uct/uct.c

   1 #include <assert.h>
   2 #include <math.h>
   3 #include <stdio.h>
   4 #include <stdlib.h>
   5 #include <string.h>
   6 #include <time.h>
   7
   8 #define DEBUG
   9
  10 #include "debug.h"
  11 #include "board.h"
  12 #include "gtp.h"
  13 #include "chat.h"
  14 #include "move.h"
  15 #include "mq.h"
  16 #include "joseki/base.h"
  17 #include "playout.h"
  18 #include "playout/moggy.h"
  19 #include "playout/light.h"
  20 #include "tactics/util.h"
  21 #include "timeinfo.h"
  22 #include "uct/dynkomi.h"
  23 #include "uct/internal.h"
  24 #include "uct/plugins.h"
  25 #include "uct/prior.h"
  26 #include "uct/search.h"
  27 #include "uct/slave.h"
  28 #include "uct/tree.h"
  29 #include "uct/uct.h"
  30 #include "uct/walk.h"
  31
  32 struct uct_policy *policy_ucb1_init(struct uct *u, char *arg);
  33 struct uct_policy *policy_ucb1amaf_init(struct uct *u, char *arg, struct board *board);
  34 static void uct_pondering_start(struct uct *u, struct board *b0, struct tree *t, enum stone color);
  35
  36 /* Maximal simulation length. */
  37 #define MC_GAMELEN      MAX_GAMELEN
  38
  39
  40 static void
  41 setup_state(struct uct *u, struct board *b, enum stone color)
  42 {
  43         u->t = tree_init(b, color, u->fast_alloc ? u->max_tree_size : 0,
  44                          u->max_pruned_size, u->pruning_threshold, u->local_tree_aging, u->stats_hbits);
  45         if (u->force_seed)
  46                 fast_srandom(u->force_seed);
  47         if (UDEBUGL(3))
  48                 fprintf(stderr, "Fresh board with random seed %lu\n", fast_getseed());
  49         if (!u->no_tbook && b->moves == 0) {
  50                 if (color == S_BLACK) {
  51                         tree_load(u->t, b);
  52                 } else if (DEBUGL(0)) {
  53                         fprintf(stderr, "Warning: First move appears to be white\n");
  54                 }
  55         }
  56 }
  57
  58 static void
  59 reset_state(struct uct *u)
  60 {
  61         assert(u->t);
  62         tree_done(u->t); u->t = NULL;
  63 }
  64
  65 static void
  66 setup_dynkomi(struct uct *u, struct board *b, enum stone to_play)
  67 {
  68         if (u->t->use_extra_komi && !u->pondering && u->dynkomi->permove)
  69                 u->t->extra_komi = u->dynkomi->permove(u->dynkomi, b, u->t);
  70         else if (!u->t->use_extra_komi)
  71                 u->t->extra_komi = 0;
  72 }
  73
  74 void
  75 uct_prepare_move(struct uct *u, struct board *b, enum stone color)
  76 {
  77         if (u->t) {
  78                 /* Verify that we have sane state. */
  79                 assert(b->es == u);
  80                 assert(u->t && b->moves);
  81                 if (color != stone_other(u->t->root_color)) {
  82                         fprintf(stderr, "Fatal: Non-alternating play detected %d %d\n",
  83                                 color, u->t->root_color);
  84                         exit(1);
  85                 }
  86                 uct_htable_reset(u->t);
  87
  88         } else {
  89                 /* We need fresh state. */
  90                 b->es = u;
  91                 setup_state(u, b, color);
  92         }
  93
  94         u->ownermap.playouts = 0;
  95         memset(u->ownermap.map, 0, board_size2(b) * sizeof(u->ownermap.map[0]));
  96         u->played_own = u->played_all = 0;
  97 }
  98
  99 static void
 100 dead_group_list(struct uct *u, struct board *b, struct move_queue *mq)
 101 {
 102         enum gj_state gs_array[board_size2(b)];
 103         struct group_judgement gj = { .thres = GJ_THRES, .gs = gs_array };
 104         board_ownermap_judge_groups(b, &u->ownermap, &gj);
 105         groups_of_status(b, &gj, GS_DEAD, mq);
 106 }
 107
 108 bool
 109 uct_pass_is_safe(struct uct *u, struct board *b, enum stone color, bool pass_all_alive)
 110 {
 111         /* Make sure enough playouts are simulated to get a reasonable dead group list. */
 112         while (u->ownermap.playouts < GJ_MINGAMES)
 113                 uct_playout(u, b, color, u->t);
 114
 115         struct move_queue mq = { .moves = 0 };
 116         dead_group_list(u, b, &mq);
 117         if (pass_all_alive) {
 118                 for (unsigned int i = 0; i < mq.moves; i++) {
 119                         if (board_at(b, mq.move[i]) == stone_other(color)) {
 120                                 return false; // We need to remove opponent dead groups first.
 121                         }
 122                 }
 123                 mq.moves = 0; // our dead stones are alive when pass_all_alive is true
 124         }
 125         if (u->allow_losing_pass) {
 126                 foreach_point(b) {
 127                         if (board_at(b, c) == S_OFFBOARD)
 128                                 continue;
 129                         if (board_ownermap_judge_point(&u->ownermap, c, GJ_THRES) == PJ_UNKNOWN) {
 130                                 if (UDEBUGL(3))
 131                                         fprintf(stderr, "uct_pass_is_safe fails at %s[%d]\n", coord2sstr(c, b), c);
 132                                 return false; // Unclear point, clarify first.
 133                         }
 134                 } foreach_point_end;
 135                 return true;
 136         }
 137         return pass_is_safe(b, color, &mq);
 138 }
 139
 140 static char *
 141 uct_printhook_ownermap(struct board *board, coord_t c, char *s, char *end)
 142 {
 143         struct uct *u = board->es;
 144         if (!u) {
 145                 strcat(s, ". ");
 146                 return s + 2;
 147         }
 148         const char chr[] = ":XO,"; // dame, black, white, unclear
 149         const char chm[] = ":xo,";
 150         char ch = chr[board_ownermap_judge_point(&u->ownermap, c, GJ_THRES)];
 151         if (ch == ',') { // less precise estimate then?
 152                 ch = chm[board_ownermap_judge_point(&u->ownermap, c, 0.67)];
 153         }
 154         s += snprintf(s, end - s, "%c ", ch);
 155         return s;
 156 }
 157
 158 static char *
 159 uct_notify_play(struct engine *e, struct board *b, struct move *m, char *enginearg)
 160 {
 161         struct uct *u = e->data;
 162         if (!u->t) {
 163                 /* No state, create one - this is probably game beginning
 164                  * and we need to load the opening tbook right now. */
 165                 uct_prepare_move(u, b, m->color);
 166                 assert(u->t);
 167         }
 168
 169         /* Stop pondering, required by tree_promote_at() */
 170         uct_pondering_stop(u);
 171         if (UDEBUGL(2) && u->slave)
 172                 tree_dump(u->t, u->dumpthres);
 173
 174         if (is_resign(m->coord)) {
 175                 /* Reset state. */
 176                 reset_state(u);
 177                 return NULL;
 178         }
 179
 180         /* Promote node of the appropriate move to the tree root. */
 181         assert(u->t->root);
 182         if (!tree_promote_at(u->t, b, m->coord)) {
 183                 if (UDEBUGL(3))
 184                         fprintf(stderr, "Warning: Cannot promote move node! Several play commands in row?\n");
 185                 reset_state(u);
 186                 return NULL;
 187         }
 188
 189         /* If we are a slave in a distributed engine, start pondering once
 190          * we know which move we actually played. See uct_genmove() about
 191          * the check for pass. */
 192         if (u->pondering_opt && u->slave && m->color == u->my_color && !is_pass(m->coord))
 193                 uct_pondering_start(u, b, u->t, stone_other(m->color));
 194
 195         return NULL;
 196 }
 197
 198 static char *
 199 uct_undo(struct engine *e, struct board *b)
 200 {
 201         struct uct *u = e->data;
 202
 203         if (!u->t) return NULL;
 204         uct_pondering_stop(u);
 205         reset_state(u);
 206         return NULL;
 207 }
 208
 209 static char *
 210 uct_result(struct engine *e, struct board *b)
 211 {
 212         struct uct *u = e->data;
 213         static char reply[1024];
 214
 215         if (!u->t)
 216                 return NULL;
 217         enum stone color = u->t->root_color;
 218         struct tree_node *n = u->t->root;
 219         snprintf(reply, 1024, "%s %s %d %.2f %.1f",
 220                  stone2str(color), coord2sstr(node_coord(n), b),
 221                  n->u.playouts, tree_node_get_value(u->t, -1, n->u.value),
 222                  u->t->use_extra_komi ? u->t->extra_komi : 0);
 223         return reply;
 224 }
 225
 226 static char *
 227 uct_chat(struct engine *e, struct board *b, bool opponent, char *from, char *cmd)
 228 {
 229         struct uct *u = e->data;
 230
 231         if (!u->t)
 232                 return generic_chat(b, opponent, from, cmd, S_NONE, pass, 0, 1, u->threads, 0.0, 0.0);
 233
 234         struct tree_node *n = u->t->root;
 235         double winrate = tree_node_get_value(u->t, -1, n->u.value);
 236         double extra_komi = u->t->use_extra_komi && abs(u->t->extra_komi) >= 0.5 ? u->t->extra_komi : 0;
 237
 238         return generic_chat(b, opponent, from, cmd, u->t->root_color, node_coord(n), n->u.playouts, 1,
 239                             u->threads, winrate, extra_komi);
 240 }
 241
 242 static void
 243 uct_dead_group_list(struct engine *e, struct board *b, struct move_queue *mq)
 244 {
 245         struct uct *u = e->data;
 246
 247         /* This means the game is probably over, no use pondering on. */
 248         uct_pondering_stop(u);
 249
 250         if (u->pass_all_alive)
 251                 return; // no dead groups
 252
 253         bool mock_state = false;
 254
 255         if (!u->t) {
 256                 /* No state, but we cannot just back out - we might
 257                  * have passed earlier, only assuming some stones are
 258                  * dead, and then re-connected, only to lose counting
 259                  * when all stones are assumed alive. */
 260                 uct_prepare_move(u, b, S_BLACK); assert(u->t);
 261                 mock_state = true;
 262         }
 263         /* Make sure the ownermap is well-seeded. */
 264         while (u->ownermap.playouts < GJ_MINGAMES)
 265                 uct_playout(u, b, S_BLACK, u->t);
 266         /* Show the ownermap: */
 267         if (DEBUGL(2))
 268                 board_print_custom(b, stderr, uct_printhook_ownermap);
 269
 270         dead_group_list(u, b, mq);
 271
 272         if (mock_state) {
 273                 /* Clean up the mock state in case we will receive
 274                  * a genmove; we could get a non-alternating-move
 275                  * error from uct_prepare_move() in that case otherwise. */
 276                 reset_state(u);
 277         }
 278 }
 279
 280 static void
 281 playout_policy_done(struct playout_policy *p)
 282 {
 283         if (p->done) p->done(p);
 284         if (p->data) free(p->data);
 285         free(p);
 286 }
 287
 288 static void
 289 uct_done(struct engine *e)
 290 {
 291         /* This is called on engine reset, especially when clear_board
 292          * is received and new game should begin. */
 293         struct uct *u = e->data;
 294         uct_pondering_stop(u);
 295         if (u->t) reset_state(u);
 296         free(u->ownermap.map);
 297
 298         free(u->policy);
 299         free(u->random_policy);
 300         playout_policy_done(u->playout);
 301         uct_prior_done(u->prior);
 302         joseki_done(u->jdict);
 303         pluginset_done(u->plugins);
 304 }
 305
 306
 307
 308 /* Run time-limited MCTS search on foreground. */
 309 static int
 310 uct_search(struct uct *u, struct board *b, struct time_info *ti, enum stone color, struct tree *t, bool print_progress)
 311 {
 312         struct uct_search_state s;
 313         uct_search_start(u, b, color, t, ti, &s);
 314         if (UDEBUGL(2) && s.base_playouts > 0)
 315                 fprintf(stderr, "<pre-simulated %d games>\n", s.base_playouts);
 316
 317         /* The search tree is ctx->t. This is currently == . It is important
 318          * to reference ctx->t directly since the
 319          * thread manager will swap the tree pointer asynchronously. */
 320
 321         /* Now, just periodically poll the search tree. */
 322         /* Note that in case of TD_GAMES, threads will not wait for
 323          * the uct_search_check_stop() signalization. */
 324         while (1) {
 325                 time_sleep(TREE_BUSYWAIT_INTERVAL);
 326                 /* TREE_BUSYWAIT_INTERVAL should never be less than desired time, or the
 327                  * time control is broken. But if it happens to be less, we still search
 328                  * at least 100ms otherwise the move is completely random. */
 329
 330                 int i = uct_search_games(&s);
 331                 /* Print notifications etc. */
 332                 uct_search_progress(u, b, color, t, ti, &s, i);
 333                 /* Check if we should stop the search. */
 334                 if (uct_search_check_stop(u, b, color, t, ti, &s, i))
 335                         break;
 336         }
 337
 338         struct uct_thread_ctx *ctx = uct_search_stop();
 339         if (UDEBUGL(2)) tree_dump(t, u->dumpthres);
 340         if (UDEBUGL(2))
 341                 fprintf(stderr, "(avg score %f/%d; dynkomi's %f/%d value %f/%d)\n",
 342                         t->avg_score.value, t->avg_score.playouts,
 343                         u->dynkomi->score.value, u->dynkomi->score.playouts,
 344                         u->dynkomi->value.value, u->dynkomi->value.playouts);
 345         if (print_progress)
 346                 uct_progress_status(u, t, color, ctx->games, NULL);
 347
 348         u->played_own += ctx->games;
 349         return ctx->games;
 350 }
 351
 352 /* Start pondering background with @color to play. */
 353 static void
 354 uct_pondering_start(struct uct *u, struct board *b0, struct tree *t, enum stone color)
 355 {
 356         if (UDEBUGL(1))
 357                 fprintf(stderr, "Starting to ponder with color %s\n", stone2str(stone_other(color)));
 358         u->pondering = true;
 359
 360         /* We need a local board copy to ponder upon. */
 361         struct board *b = malloc2(sizeof(*b)); board_copy(b, b0);
 362
 363         /* *b0 did not have the genmove'd move played yet. */
 364         struct move m = { node_coord(t->root), t->root_color };
 365         int res = board_play(b, &m);
 366         assert(res >= 0);
 367         setup_dynkomi(u, b, stone_other(m.color));
 368
 369         /* Start MCTS manager thread "headless". */
 370         static struct uct_search_state s;
 371         uct_search_start(u, b, color, t, NULL, &s);
 372 }
 373
 374 /* uct_search_stop() frontend for the pondering (non-genmove) mode, and
 375  * to stop the background search for a slave in the distributed engine. */
 376 void
 377 uct_pondering_stop(struct uct *u)
 378 {
 379         if (!thread_manager_running)
 380                 return;
 381
 382         /* Stop the thread manager. */
 383         struct uct_thread_ctx *ctx = uct_search_stop();
 384         if (UDEBUGL(1)) {
 385                 if (u->pondering) fprintf(stderr, "(pondering) ");
 386                 uct_progress_status(u, ctx->t, ctx->color, ctx->games, NULL);
 387         }
 388         if (u->pondering) {
 389                 free(ctx->b);
 390                 u->pondering = false;
 391         }
 392 }
 393
 394
 395 void
 396 uct_genmove_setup(struct uct *u, struct board *b, enum stone color)
 397 {
 398         if (b->superko_violation) {
 399                 fprintf(stderr, "!!! WARNING: SUPERKO VIOLATION OCCURED BEFORE THIS MOVE\n");
 400                 fprintf(stderr, "Maybe you play with situational instead of positional superko?\n");
 401                 fprintf(stderr, "I'm going to ignore the violation, but note that I may miss\n");
 402                 fprintf(stderr, "some moves valid under this ruleset because of this.\n");
 403                 b->superko_violation = false;
 404         }
 405
 406         uct_prepare_move(u, b, color);
 407
 408         assert(u->t);
 409         u->my_color = color;
 410
 411         /* How to decide whether to use dynkomi in this game? Since we use
 412          * pondering, it's not simple "who-to-play" matter. Decide based on
 413          * the last genmove issued. */
 414         u->t->use_extra_komi = !!(u->dynkomi_mask & color);
 415         setup_dynkomi(u, b, color);
 416
 417         if (b->rules == RULES_JAPANESE)
 418                 u->territory_scoring = true;
 419
 420         /* Make pessimistic assumption about komi for Japanese rules to
 421          * avoid losing by 0.5 when winning by 0.5 with Chinese rules.
 422          * The rules usually give the same winner if the integer part of komi
 423          * is odd so we adjust the komi only if it is even (for a board of
 424          * odd size). We are not trying  to get an exact evaluation for rare
 425          * cases of seki. For details see http://home.snafu.de/jasiek/parity.html */
 426         if (u->territory_scoring && (((int)floor(b->komi) + board_size(b)) & 1)) {
 427                 b->komi += (color == S_BLACK ? 1.0 : -1.0);
 428                 if (UDEBUGL(0))
 429                         fprintf(stderr, "Setting komi to %.1f assuming Japanese rules\n",
 430                                 b->komi);
 431         }
 432 }
 433
 434 static coord_t *
 435 uct_genmove(struct engine *e, struct board *b, struct time_info *ti, enum stone color, bool pass_all_alive)
 436 {
 437         double start_time = time_now();
 438         struct uct *u = e->data;
 439         u->pass_all_alive |= pass_all_alive;
 440         uct_pondering_stop(u);
 441         uct_genmove_setup(u, b, color);
 442
 443         /* Start the Monte Carlo Tree Search! */
 444         int base_playouts = u->t->root->u.playouts;
 445         int played_games = uct_search(u, b, ti, color, u->t, false);
 446
 447         coord_t best_coord;
 448         struct tree_node *best;
 449         best = uct_search_result(u, b, color, u->pass_all_alive, played_games, base_playouts, &best_coord);
 450
 451         if (UDEBUGL(2)) {
 452                 double time = time_now() - start_time + 0.000001; /* avoid divide by zero */
 453                 fprintf(stderr, "genmove in %0.2fs (%d games/s, %d games/s/thread)\n",
 454                         time, (int)(played_games/time), (int)(played_games/time/u->threads));
 455         }
 456
 457         uct_progress_status(u, u->t, color, played_games, &best_coord);
 458
 459         if (!best) {
 460                 /* Pass or resign. */
 461                 reset_state(u);
 462                 return coord_copy(best_coord);
 463         }
 464         tree_promote_node(u->t, &best);
 465
 466         /* After a pass, pondering is harmful for two reasons:
 467          * (i) We might keep pondering even when the game is over.
 468          * Of course this is the case for opponent resign as well.
 469          * (ii) More importantly, the ownermap will get skewed since
 470          * the UCT will start cutting off any playouts. */
 471         if (u->pondering_opt && !is_pass(node_coord(best))) {
 472                 uct_pondering_start(u, b, u->t, stone_other(color));
 473         }
 474         return coord_copy(best_coord);
 475 }
 476
 477
 478 bool
 479 uct_gentbook(struct engine *e, struct board *b, struct time_info *ti, enum stone color)
 480 {
 481         struct uct *u = e->data;
 482         if (!u->t) uct_prepare_move(u, b, color);
 483         assert(u->t);
 484
 485         if (ti->dim == TD_GAMES) {
 486                 /* Don't count in games that already went into the tbook. */
 487                 ti->len.games += u->t->root->u.playouts;
 488         }
 489         uct_search(u, b, ti, color, u->t, true);
 490
 491         assert(ti->dim == TD_GAMES);
 492         tree_save(u->t, b, ti->len.games / 100);
 493
 494         return true;
 495 }
 496
 497 void
 498 uct_dumptbook(struct engine *e, struct board *b, enum stone color)
 499 {
 500         struct uct *u = e->data;
 501         struct tree *t = tree_init(b, color, u->fast_alloc ? u->max_tree_size : 0,
 502                          u->max_pruned_size, u->pruning_threshold, u->local_tree_aging, 0);
 503         tree_load(t, b);
 504         tree_dump(t, 0);
 505         tree_done(t);
 506 }
 507
 508
 509 floating_t
 510 uct_evaluate_one(struct engine *e, struct board *b, struct time_info *ti, coord_t c, enum stone color)
 511 {
 512         struct uct *u = e->data;
 513
 514         struct board b2;
 515         board_copy(&b2, b);
 516         struct move m = { c, color };
 517         int res = board_play(&b2, &m);
 518         if (res < 0)
 519                 return NAN;
 520         color = stone_other(color);
 521
 522         if (u->t) reset_state(u);
 523         uct_prepare_move(u, &b2, color);
 524         assert(u->t);
 525
 526         floating_t bestval;
 527         uct_search(u, &b2, ti, color, u->t, true);
 528         struct tree_node *best = u->policy->choose(u->policy, u->t->root, &b2, color, resign);
 529         if (!best) {
 530                 bestval = NAN; // the opponent has no reply!
 531         } else {
 532                 bestval = tree_node_get_value(u->t, 1, best->u.value);
 533         }
 534
 535         reset_state(u); // clean our junk
 536
 537         return isnan(bestval) ? NAN : 1.0f - bestval;
 538 }
 539
 540 void
 541 uct_evaluate(struct engine *e, struct board *b, struct time_info *ti, floating_t *vals, enum stone color)
 542 {
 543         for (int i = 0; i < b->flen; i++) {
 544                 if (is_pass(b->f[i]))
 545                         vals[i] = NAN;
 546                 else
 547                         vals[i] = uct_evaluate_one(e, b, ti, b->f[i], color);
 548         }
 549 }
 550
 551
 552 struct uct *
 553 uct_state_init(char *arg, struct board *b)
 554 {
 555         struct uct *u = calloc2(1, sizeof(struct uct));
 556         bool pat_setup = false;
 557
 558         u->debug_level = debug_level;
 559         u->reportfreq = 10000;
 560         u->gamelen = MC_GAMELEN;
 561         u->resign_threshold = 0.2;
 562         u->sure_win_threshold = 0.9;
 563         u->mercymin = 0;
 564         u->significant_threshold = 50;
 565         u->expand_p = 8;
 566         u->dumpthres = 1000;
 567         u->playout_amaf = true;
 568         u->amaf_prior = false;
 569         u->max_tree_size = 1408ULL * 1048576;
 570         u->fast_alloc = true;
 571         u->pruning_threshold = 0;
 572
 573         u->threads = 1;
 574         u->thread_model = TM_TREEVL;
 575         u->virtual_loss = 1;
 576
 577         u->fuseki_end = 20; // max time at 361*20% = 72 moves (our 36th move, still 99 to play)
 578         u->yose_start = 40; // (100-40-25)*361/100/2 = 63 moves still to play by us then
 579         u->bestr_ratio = 0.02;
 580         // 2.5 is clearly too much, but seems to compensate well for overly stern time allocations.
 581         // TODO: Further tuning and experiments with better time allocation schemes.
 582         u->best2_ratio = 2.5;
 583         u->max_maintime_ratio = 3.0;
 584
 585         u->val_scale = 0; u->val_points = 40;
 586         u->dynkomi_interval = 1000;
 587         u->dynkomi_mask = S_BLACK | S_WHITE;
 588
 589         u->tenuki_d = 4;
 590         u->local_tree_aging = 80;
 591         u->local_tree_depth_decay = 1.5;
 592         u->local_tree_eval = LTE_ROOT;
 593         u->local_tree_neival = true;
 594
 595         u->max_slaves = -1;
 596         u->slave_index = -1;
 597         u->stats_delay = 0.01; // 10 ms
 598
 599         u->plugins = pluginset_init(b);
 600
 601         u->jdict = joseki_load(b->size);
 602
 603         if (arg) {
 604                 char *optspec, *next = arg;
 605                 while (*next) {
 606                         optspec = next;
 607                         next += strcspn(next, ",");
 608                         if (*next) { *next++ = 0; } else { *next = 0; }
 609
 610                         char *optname = optspec;
 611                         char *optval = strchr(optspec, '=');
 612                         if (optval) *optval++ = 0;
 613
 614                         /** Basic options */
 615
 616                         if (!strcasecmp(optname, "debug")) {
 617                                 if (optval)
 618                                         u->debug_level = atoi(optval);
 619                                 else
 620                                         u->debug_level++;
 621                         } else if (!strcasecmp(optname, "reporting") && optval) {
 622                                 /* The format of output for detailed progress
 623                                  * information (such as current best move and
 624                                  * its value, etc.). */
 625                                 if (!strcasecmp(optval, "text")) {
 626                                         /* Plaintext traditional output. */
 627                                         u->reporting = UR_TEXT;
 628                                 } else if (!strcasecmp(optval, "json")) {
 629                                         /* JSON output. Implies debug=0. */
 630                                         u->reporting = UR_JSON;
 631                                         u->debug_level = 0;
 632                                 } else if (!strcasecmp(optval, "jsonbig")) {
 633                                         /* JSON output, but much more detailed.
 634                                          * Implies debug=0. */
 635                                         u->reporting = UR_JSON_BIG;
 636                                         u->debug_level = 0;
 637                                 } else {
 638                                         fprintf(stderr, "UCT: Invalid reporting format %s\n", optval);
 639                                         exit(1);
 640                                 }
 641                         } else if (!strcasecmp(optname, "reportfreq") && optval) {
 642                                 /* The progress information line will be shown
 643                                  * every <reportfreq> simulations. */
 644                                 u->reportfreq = atoi(optval);
 645                         } else if (!strcasecmp(optname, "dumpthres") && optval) {
 646                                 /* When dumping the UCT tree on output, include
 647                                  * nodes with at least this many playouts.
 648                                  * (This value is re-scaled "intelligently"
 649                                  * in case of very large trees.) */
 650                                 u->dumpthres = atoi(optval);
 651                         } else if (!strcasecmp(optname, "resign_threshold") && optval) {
 652                                 /* Resign when this ratio of games is lost
 653                                  * after GJ_MINGAMES sample is taken. */
 654                                 u->resign_threshold = atof(optval);
 655                         } else if (!strcasecmp(optname, "sure_win_threshold") && optval) {
 656                                 /* Stop reading when this ratio of games is won
 657                                  * after PLAYOUT_EARLY_BREAK_MIN sample is
 658                                  * taken. (Prevents stupid time losses,
 659                                  * friendly to human opponents.) */
 660                                 u->sure_win_threshold = atof(optval);
 661                         } else if (!strcasecmp(optname, "force_seed") && optval) {
 662                                 /* Set RNG seed at the tree setup. */
 663                                 u->force_seed = atoi(optval);
 664                         } else if (!strcasecmp(optname, "no_tbook")) {
 665                                 /* Disable UCT opening tbook. */
 666                                 u->no_tbook = true;
 667                         } else if (!strcasecmp(optname, "pass_all_alive")) {
 668                                 /* Whether to consider passing only after all
 669                                  * dead groups were removed from the board;
 670                                  * this is like all genmoves are in fact
 671                                  * kgs-genmove_cleanup. */
 672                                 u->pass_all_alive = !optval || atoi(optval);
 673                         } else if (!strcasecmp(optname, "allow_losing_pass")) {
 674                                 /* Whether to consider passing in a clear
 675                                  * but losing situation, to be scored as a loss
 676                                  * for us. */
 677                                 u->allow_losing_pass = !optval || atoi(optval);
 678                         } else if (!strcasecmp(optname, "territory_scoring")) {
 679                                 /* Use territory scoring (default is area scoring).
 680                                  * An explicit kgs-rules command overrides this. */
 681                                 u->territory_scoring = !optval || atoi(optval);
 682                         } else if (!strcasecmp(optname, "stones_only")) {
 683                                 /* Do not count eyes. Nice to teach go to kids.
 684                                  * http://strasbourg.jeudego.org/regle_strasbourgeoise.htm */
 685                                 b->rules = RULES_STONES_ONLY;
 686                                 u->pass_all_alive = true;
 687                         } else if (!strcasecmp(optname, "banner") && optval) {
 688                                 /* Additional banner string. This must come as the
 689                                  * last engine parameter. */
 690                                 if (*next) *--next = ',';
 691                                 u->banner = strdup(optval);
 692                                 break;
 693                         } else if (!strcasecmp(optname, "plugin") && optval) {
 694                                 /* Load an external plugin; filename goes before the colon,
 695                                  * extra arguments after the colon. */
 696                                 char *pluginarg = strchr(optval, ':');
 697                                 if (pluginarg)
 698                                         *pluginarg++ = 0;
 699                                 plugin_load(u->plugins, optval, pluginarg);
 700
 701                         /** UCT behavior and policies */
 702
 703                         } else if ((!strcasecmp(optname, "policy")
 704                                 /* Node selection policy. ucb1amaf is the
 705                                  * default policy implementing RAVE, while
 706                                  * ucb1 is the simple exploration/exploitation
 707                                  * policy. Policies can take further extra
 708                                  * options. */
 709                                     || !strcasecmp(optname, "random_policy")) && optval) {
 710                                 /* A policy to be used randomly with small
 711                                  * chance instead of the default policy. */
 712                                 char *policyarg = strchr(optval, ':');
 713                                 struct uct_policy **p = !strcasecmp(optname, "policy") ? &u->policy : &u->random_policy;
 714                                 if (policyarg)
 715                                         *policyarg++ = 0;
 716                                 if (!strcasecmp(optval, "ucb1")) {
 717                                         *p = policy_ucb1_init(u, policyarg);
 718                                 } else if (!strcasecmp(optval, "ucb1amaf")) {
 719                                         *p = policy_ucb1amaf_init(u, policyarg, b);
 720                                 } else {
 721                                         fprintf(stderr, "UCT: Invalid tree policy %s\n", optval);
 722                                         exit(1);
 723                                 }
 724                         } else if (!strcasecmp(optname, "playout") && optval) {
 725                                 /* Random simulation (playout) policy.
 726                                  * moggy is the default policy with large
 727                                  * amount of domain-specific knowledge and
 728                                  * heuristics. light is a simple uniformly
 729                                  * random move selection policy. */
 730                                 char *playoutarg = strchr(optval, ':');
 731                                 if (playoutarg)
 732                                         *playoutarg++ = 0;
 733                                 if (!strcasecmp(optval, "moggy")) {
 734                                         u->playout = playout_moggy_init(playoutarg, b, u->jdict);
 735                                 } else if (!strcasecmp(optval, "light")) {
 736                                         u->playout = playout_light_init(playoutarg, b);
 737                                 } else {
 738                                         fprintf(stderr, "UCT: Invalid playout policy %s\n", optval);
 739                                         exit(1);
 740                                 }
 741                         } else if (!strcasecmp(optname, "prior") && optval) {
 742                                 /* Node priors policy. When expanding a node,
 743                                  * it will seed node values heuristically
 744                                  * (most importantly, based on playout policy
 745                                  * opinion, but also with regard to other
 746                                  * things). See uct/prior.c for details.
 747                                  * Use prior=eqex=0 to disable priors. */
 748                                 u->prior = uct_prior_init(optval, b, u);
 749                         } else if (!strcasecmp(optname, "mercy") && optval) {
 750                                 /* Minimal difference of black/white captures
 751                                  * to stop playout - "Mercy Rule". Speeds up
 752                                  * hopeless playouts at the expense of some
 753                                  * accuracy. */
 754                                 u->mercymin = atoi(optval);
 755                         } else if (!strcasecmp(optname, "gamelen") && optval) {
 756                                 /* Maximum length of single simulation
 757                                  * in moves. */
 758                                 u->gamelen = atoi(optval);
 759                         } else if (!strcasecmp(optname, "expand_p") && optval) {
 760                                 /* Expand UCT nodes after it has been
 761                                  * visited this many times. */
 762                                 u->expand_p = atoi(optval);
 763                         } else if (!strcasecmp(optname, "random_policy_chance") && optval) {
 764                                 /* If specified (N), with probability 1/N, random_policy policy
 765                                  * descend is used instead of main policy descend; useful
 766                                  * if specified policy (e.g. UCB1AMAF) can make unduly biased
 767                                  * choices sometimes, you can fall back to e.g.
 768                                  * random_policy=UCB1. */
 769                                 u->random_policy_chance = atoi(optval);
 770
 771                         /** General AMAF behavior */
 772                         /* (Only relevant if the policy supports AMAF.
 773                          * More variables can be tuned as policy
 774                          * parameters.) */
 775
 776                         } else if (!strcasecmp(optname, "playout_amaf")) {
 777                                 /* Whether to include random playout moves in
 778                                  * AMAF as well. (Otherwise, only tree moves
 779                                  * are included in AMAF. Of course makes sense
 780                                  * only in connection with an AMAF policy.) */
 781                                 /* with-without: 55.5% (+-4.1) */
 782                                 if (optval && *optval == '0')
 783                                         u->playout_amaf = false;
 784                                 else
 785                                         u->playout_amaf = true;
 786                         } else if (!strcasecmp(optname, "playout_amaf_cutoff") && optval) {
 787                                 /* Keep only first N% of playout stage AMAF
 788                                  * information. */
 789                                 u->playout_amaf_cutoff = atoi(optval);
 790                         } else if (!strcasecmp(optname, "amaf_prior") && optval) {
 791                                 /* In node policy, consider prior values
 792                                  * part of the real result term or part
 793                                  * of the AMAF term? */
 794                                 u->amaf_prior = atoi(optval);
 795
 796                         /** Performance and memory management */
 797
 798                         } else if (!strcasecmp(optname, "threads") && optval) {
 799                                 /* By default, Pachi will run with only single
 800                                  * tree search thread! */
 801                                 u->threads = atoi(optval);
 802                         } else if (!strcasecmp(optname, "thread_model") && optval) {
 803                                 if (!strcasecmp(optval, "tree")) {
 804                                         /* Tree parallelization - all threads
 805                                          * grind on the same tree. */
 806                                         u->thread_model = TM_TREE;
 807                                         u->virtual_loss = 0;
 808                                 } else if (!strcasecmp(optval, "treevl")) {
 809                                         /* Tree parallelization, but also
 810                                          * with virtual losses - this discou-
 811                                          * rages most threads choosing the
 812                                          * same tree branches to read. */
 813                                         u->thread_model = TM_TREEVL;
 814                                 } else {
 815                                         fprintf(stderr, "UCT: Invalid thread model %s\n", optval);
 816                                         exit(1);
 817                                 }
 818                         } else if (!strcasecmp(optname, "virtual_loss")) {
 819                                 /* Number of virtual losses added before evaluating a node. */
 820                                 u->virtual_loss = !optval || atoi(optval);
 821                         } else if (!strcasecmp(optname, "pondering")) {
 822                                 /* Keep searching even during opponent's turn. */
 823                                 u->pondering_opt = !optval || atoi(optval);
 824                         } else if (!strcasecmp(optname, "max_tree_size") && optval) {
 825                                 /* Maximum amount of memory [MiB] consumed by the move tree.
 826                                  * For fast_alloc it includes the temp tree used for pruning.
 827                                  * Default is 3072 (3 GiB). */
 828                                 u->max_tree_size = atol(optval) * 1048576;
 829                         } else if (!strcasecmp(optname, "fast_alloc")) {
 830                                 u->fast_alloc = !optval || atoi(optval);
 831                         } else if (!strcasecmp(optname, "pruning_threshold") && optval) {
 832                                 /* Force pruning at beginning of a move if the tree consumes
 833                                  * more than this [MiB]. Default is 10% of max_tree_size.
 834                                  * Increase to reduce pruning time overhead if memory is plentiful.
 835                                  * This option is meaningful only for fast_alloc. */
 836                                 u->pruning_threshold = atol(optval) * 1048576;
 837
 838                         /** Time control */
 839
 840                         } else if (!strcasecmp(optname, "best2_ratio") && optval) {
 841                                 /* If set, prolong simulating while
 842                                  * first_best/second_best playouts ratio
 843                                  * is less than best2_ratio. */
 844                                 u->best2_ratio = atof(optval);
 845                         } else if (!strcasecmp(optname, "bestr_ratio") && optval) {
 846                                 /* If set, prolong simulating while
 847                                  * best,best_best_child values delta
 848                                  * is more than bestr_ratio. */
 849                                 u->bestr_ratio = atof(optval);
 850                         } else if (!strcasecmp(optname, "max_maintime_ratio") && optval) {
 851                                 /* If set and while not in byoyomi, prolong simulating no more than
 852                                  * max_maintime_ratio times the normal desired thinking time. */
 853                                 u->max_maintime_ratio = atof(optval);
 854                         } else if (!strcasecmp(optname, "fuseki_end") && optval) {
 855                                 /* At the very beginning it's not worth thinking
 856                                  * too long because the playout evaluations are
 857                                  * very noisy. So gradually increase the thinking
 858                                  * time up to maximum when fuseki_end percent
 859                                  * of the board has been played.
 860                                  * This only applies if we are not in byoyomi. */
 861                                 u->fuseki_end = atoi(optval);
 862                         } else if (!strcasecmp(optname, "yose_start") && optval) {
 863                                 /* When yose_start percent of the board has been
 864                                  * played, or if we are in byoyomi, stop spending
 865                                  * more time and spread the remaining time
 866                                  * uniformly.
 867                                  * Between fuseki_end and yose_start, we spend
 868                                  * a constant proportion of the remaining time
 869                                  * on each move. (yose_start should actually
 870                                  * be much earlier than when real yose start,
 871                                  * but "yose" is a good short name to convey
 872                                  * the idea.) */
 873                                 u->yose_start = atoi(optval);
 874
 875                         /** Dynamic komi */
 876
 877                         } else if (!strcasecmp(optname, "dynkomi") && optval) {
 878                                 /* Dynamic komi approach; there are multiple
 879                                  * ways to adjust komi dynamically throughout
 880                                  * play. We currently support two: */
 881                                 char *dynkomiarg = strchr(optval, ':');
 882                                 if (dynkomiarg)
 883                                         *dynkomiarg++ = 0;
 884                                 if (!strcasecmp(optval, "none")) {
 885                                         u->dynkomi = uct_dynkomi_init_none(u, dynkomiarg, b);
 886                                 } else if (!strcasecmp(optval, "linear")) {
 887                                         /* You should set dynkomi_mask=1 or a very low
 888                                          * handicap_value for white. */
 889                                         u->dynkomi = uct_dynkomi_init_linear(u, dynkomiarg, b);
 890                                 } else if (!strcasecmp(optval, "adaptive")) {
 891                                         /* There are many more knobs to
 892                                          * crank - see uct/dynkomi.c. */
 893                                         u->dynkomi = uct_dynkomi_init_adaptive(u, dynkomiarg, b);
 894                                 } else {
 895                                         fprintf(stderr, "UCT: Invalid dynkomi mode %s\n", optval);
 896                                         exit(1);
 897                                 }
 898                         } else if (!strcasecmp(optname, "dynkomi_mask") && optval) {
 899                                 /* Bitmask of colors the player must be
 900                                  * for dynkomi be applied; the default dynkomi_mask=3 allows
 901                                  * dynkomi even in games where Pachi is white. */
 902                                 u->dynkomi_mask = atoi(optval);
 903                         } else if (!strcasecmp(optname, "dynkomi_interval") && optval) {
 904                                 /* If non-zero, re-adjust dynamic komi
 905                                  * throughout a single genmove reading,
 906                                  * roughly every N simulations. */
 907                                 /* XXX: Does not work with tree
 908                                  * parallelization. */
 909                                 u->dynkomi_interval = atoi(optval);
 910
 911                         /** Node value result scaling */
 912
 913                         } else if (!strcasecmp(optname, "val_scale") && optval) {
 914                                 /* How much of the game result value should be
 915                                  * influenced by win size. Zero means it isn't. */
 916                                 u->val_scale = atof(optval);
 917                         } else if (!strcasecmp(optname, "val_points") && optval) {
 918                                 /* Maximum size of win to be scaled into game
 919                                  * result value. Zero means boardsize^2. */
 920                                 u->val_points = atoi(optval) * 2; // result values are doubled
 921                         } else if (!strcasecmp(optname, "val_extra")) {
 922                                 /* If false, the score coefficient will be simply
 923                                  * added to the value, instead of scaling the result
 924                                  * coefficient because of it. */
 925                                 u->val_extra = !optval || atoi(optval);
 926                         } else if (!strcasecmp(optname, "val_byavg")) {
 927                                 /* If true, the score included in the value will
 928                                  * be relative to average score in the current
 929                                  * search episode inst. of jigo. */
 930                                 u->val_byavg = !optval || atoi(optval);
 931                         } else if (!strcasecmp(optname, "val_bytemp")) {
 932                                 /* If true, the value scaling coefficient
 933                                  * is different based on value extremity
 934                                  * (dist. from 0.5), linear between
 935                                  * val_bytemp_min, val_scale. */
 936                                 u->val_bytemp = !optval || atoi(optval);
 937                         } else if (!strcasecmp(optname, "val_bytemp_min") && optval) {
 938                                 /* Minimum val_scale in case of val_bytemp. */
 939                                 u->val_bytemp_min = atof(optval);
 940
 941                         /** Local trees */
 942                         /* (Purely experimental. Does not work - yet!) */
 943
 944                         } else if (!strcasecmp(optname, "local_tree")) {
 945                                 /* Whether to bias exploration by local tree values. */
 946                                 u->local_tree = !optval || atoi(optval);
 947                         } else if (!strcasecmp(optname, "tenuki_d") && optval) {
 948                                 /* Tenuki distance at which to break the local tree. */
 949                                 u->tenuki_d = atoi(optval);
 950                                 if (u->tenuki_d > TREE_NODE_D_MAX + 1) {
 951                                         fprintf(stderr, "uct: tenuki_d must not be larger than TREE_NODE_D_MAX+1 %d\n", TREE_NODE_D_MAX + 1);
 952                                         exit(1);
 953                                 }
 954                         } else if (!strcasecmp(optname, "local_tree_aging") && optval) {
 955                                 /* How much to reduce local tree values between moves. */
 956                                 u->local_tree_aging = atof(optval);
 957                         } else if (!strcasecmp(optname, "local_tree_depth_decay") && optval) {
 958                                 /* With value x>0, during the descent the node
 959                                  * contributes 1/x^depth playouts in
 960                                  * the local tree. I.e., with x>1, nodes more
 961                                  * distant from local situation contribute more
 962                                  * than nodes near the root. */
 963                                 u->local_tree_depth_decay = atof(optval);
 964                         } else if (!strcasecmp(optname, "local_tree_allseq")) {
 965                                 /* If disabled, only complete sequences are stored
 966                                  * in the local tree. If this is on, also
 967                                  * subsequences starting at each move are stored. */
 968                                 u->local_tree_allseq = !optval || atoi(optval);
 969                         } else if (!strcasecmp(optname, "local_tree_neival")) {
 970                                 /* If disabled, local node value is not
 971                                  * computed just based on terminal status
 972                                  * of the coordinate, but also its neighbors. */
 973                                 u->local_tree_neival = !optval || atoi(optval);
 974                         } else if (!strcasecmp(optname, "local_tree_eval")) {
 975                                 /* How is the value inserted in the local tree
 976                                  * determined. */
 977                                 if (!strcasecmp(optval, "root"))
 978                                         /* All moves within a tree branch are
 979                                          * considered wrt. their merit
 980                                          * reaching tachtical goal of making
 981                                          * the first move in the branch
 982                                          * survive. */
 983                                         u->local_tree_eval = LTE_ROOT;
 984                                 else if (!strcasecmp(optval, "each"))
 985                                         /* Each move is considered wrt.
 986                                          * its own survival. */
 987                                         u->local_tree_eval = LTE_EACH;
 988                                 else if (!strcasecmp(optval, "total"))
 989                                         /* The tactical goal is the survival
 990                                          * of all the moves of my color and
 991                                          * non-survival of all the opponent
 992                                          * moves. Local values (and their
 993                                          * inverses) are averaged. */
 994                                         u->local_tree_eval = LTE_TOTAL;
 995                                 else {
 996                                         fprintf(stderr, "uct: unknown local_tree_eval %s\n", optval);
 997                                         exit(1);
 998                                 }
 999                         } else if (!strcasecmp(optname, "local_tree_rootchoose")) {
1000                                 /* If disabled, only moves within the local
1001                                  * tree branch are considered; the values
1002                                  * of the branch roots (i.e. root children)
1003                                  * are ignored. This may make sense together
1004                                  * with eval!=each, we consider only moves
1005                                  * that influence the goal, not the "rating"
1006                                  * of the goal itself. (The real solution
1007                                  * will be probably using criticality to pick
1008                                  * local tree branches.) */
1009                                 u->local_tree_rootchoose = !optval || atoi(optval);
1010
1011                         /** Other heuristics */
1012                         } else if (!strcasecmp(optname, "patterns")) {
1013                                 /* Load pattern database. Various modules
1014                                  * (priors, policies etc.) may make use
1015                                  * of this database. They will request
1016                                  * it automatically in that case, but you
1017                                  * can use this option to tweak the pattern
1018                                  * parameters. */
1019                                 patterns_init(&u->pat, optval, false, true);
1020                                 u->want_pat = pat_setup = true;
1021                         } else if (!strcasecmp(optname, "significant_threshold") && optval) {
1022                                 /* Some heuristics (XXX: none in mainline) rely
1023                                  * on the knowledge of the last "significant"
1024                                  * node in the descent. Such a node is
1025                                  * considered reasonably trustworthy to carry
1026                                  * some meaningful information in the values
1027                                  * of the node and its children. */
1028                                 u->significant_threshold = atoi(optval);
1029
1030                         /** Distributed engine slaves setup */
1031
1032                         } else if (!strcasecmp(optname, "slave")) {
1033                                 /* Act as slave for the distributed engine. */
1034                                 u->slave = !optval || atoi(optval);
1035                         } else if (!strcasecmp(optname, "slave_index") && optval) {
1036                                 /* Optional index if per-slave behavior is desired.
1037                                  * Must be given as index/max */
1038                                 u->slave_index = atoi(optval);
1039                                 char *p = strchr(optval, '/');
1040                                 if (p) u->max_slaves = atoi(++p);
1041                         } else if (!strcasecmp(optname, "shared_nodes") && optval) {
1042                                 /* Share at most shared_nodes between master and slave at each genmoves.
1043                                  * Must use the same value in master and slaves. */
1044                                 u->shared_nodes = atoi(optval);
1045                         } else if (!strcasecmp(optname, "shared_levels") && optval) {
1046                                 /* Share only nodes of level <= shared_levels. */
1047                                 u->shared_levels = atoi(optval);
1048                         } else if (!strcasecmp(optname, "stats_hbits") && optval) {
1049                                 /* Set hash table size to 2^stats_hbits for the shared stats. */
1050                                 u->stats_hbits = atoi(optval);
1051                         } else if (!strcasecmp(optname, "stats_delay") && optval) {
1052                                 /* How long to wait in slave for initial stats to build up before
1053                                  * replying to the genmoves command (in ms) */
1054                                 u->stats_delay = 0.001 * atof(optval);
1055
1056                         /** Presets */
1057
1058                         } else if (!strcasecmp(optname, "maximize_score")) {
1059                                 /* A combination of settings that will make
1060                                  * Pachi try to maximize his points (instead
1061                                  * of playing slack yose) or minimize his loss
1062                                  * (and proceed to counting even when losing). */
1063                                 /* Please note that this preset might be
1064                                  * somewhat weaker than normal Pachi, and the
1065                                  * score maximization is approximate; point size
1066                                  * of win/loss still should not be used to judge
1067                                  * strength of Pachi or the opponent. */
1068                                 /* See README for some further notes. */
1069                                 if (!optval || atoi(optval)) {
1070                                         /* Allow scoring a lost game. */
1071                                         u->allow_losing_pass = true;
1072                                         /* Make Pachi keep his calm when losing
1073                                          * and/or maintain winning marging. */
1074                                         /* Do not play games that are losing
1075                                          * by too much. */
1076                                         /* XXX: komi_ratchet_age=40000 is necessary
1077                                          * with losing_komi_ratchet, but 40000
1078                                          * is somewhat arbitrary value. */
1079                                         char dynkomi_args[] = "losing_komi_ratchet:komi_ratchet_age=60000:no_komi_at_game_end=0:max_losing_komi=30";
1080                                         u->dynkomi = uct_dynkomi_init_adaptive(u, dynkomi_args, b);
1081                                         /* XXX: Values arbitrary so far. */
1082                                         /* XXX: Also, is bytemp sensible when
1083                                          * combined with dynamic komi?! */
1084                                         u->val_scale = 0.01;
1085                                         u->val_bytemp = true;
1086                                         u->val_bytemp_min = 0.001;
1087                                         u->val_byavg = true;
1088                                 }
1089
1090                         } else {
1091                                 fprintf(stderr, "uct: Invalid engine argument %s or missing value\n", optname);
1092                                 exit(1);
1093                         }
1094                 }
1095         }
1096
1097         if (!u->policy)
1098                 u->policy = policy_ucb1amaf_init(u, NULL, b);
1099
1100         if (!!u->random_policy_chance ^ !!u->random_policy) {
1101                 fprintf(stderr, "uct: Only one of random_policy and random_policy_chance is set\n");
1102                 exit(1);
1103         }
1104
1105         if (!u->local_tree) {
1106                 /* No ltree aging. */
1107                 u->local_tree_aging = 1.0f;
1108         }
1109
1110         if (u->fast_alloc) {
1111                 if (u->pruning_threshold < u->max_tree_size / 10)
1112                         u->pruning_threshold = u->max_tree_size / 10;
1113                 if (u->pruning_threshold > u->max_tree_size / 2)
1114                         u->pruning_threshold = u->max_tree_size / 2;
1115
1116                 /* Limit pruning temp space to 20% of memory. Beyond this we discard
1117                  * the nodes and recompute them at the next move if necessary. */
1118                 u->max_pruned_size = u->max_tree_size / 5;
1119                 u->max_tree_size -= u->max_pruned_size;
1120         } else {
1121                 /* Reserve 5% memory in case the background free() are slower
1122                  * than the concurrent allocations. */
1123                 u->max_tree_size -= u->max_tree_size / 20;
1124         }
1125
1126         if (!u->prior)
1127                 u->prior = uct_prior_init(NULL, b, u);
1128
1129         if (!u->playout)
1130                 u->playout = playout_moggy_init(NULL, b, u->jdict);
1131         if (!u->playout->debug_level)
1132                 u->playout->debug_level = u->debug_level;
1133
1134         if (u->want_pat && !pat_setup)
1135                 patterns_init(&u->pat, NULL, false, true);
1136
1137         u->ownermap.map = malloc2(board_size2(b) * sizeof(u->ownermap.map[0]));
1138
1139         if (u->slave) {
1140                 if (!u->stats_hbits) u->stats_hbits = DEFAULT_STATS_HBITS;
1141                 if (!u->shared_nodes) u->shared_nodes = DEFAULT_SHARED_NODES;
1142                 assert(u->shared_levels * board_bits2(b) <= 8 * (int)sizeof(path_t));
1143         }
1144
1145         if (!u->dynkomi)
1146                 u->dynkomi = uct_dynkomi_init_linear(u, NULL, b);
1147
1148         /* Some things remain uninitialized for now - the opening tbook
1149          * is not loaded and the tree not set up. */
1150         /* This will be initialized in setup_state() at the first move
1151          * received/requested. This is because right now we are not aware
1152          * about any komi or handicap setup and such. */
1153
1154         return u;
1155 }
1156
1157 struct engine *
1158 engine_uct_init(char *arg, struct board *b)
1159 {
1160         struct uct *u = uct_state_init(arg, b);
1161         struct engine *e = calloc2(1, sizeof(struct engine));
1162         e->name = "UCT";
1163         e->printhook = uct_printhook_ownermap;
1164         e->notify_play = uct_notify_play;
1165         e->chat = uct_chat;
1166         e->undo = uct_undo;
1167         e->result = uct_result;
1168         e->genmove = uct_genmove;
1169         e->genmoves = uct_genmoves;
1170         e->evaluate = uct_evaluate;
1171         e->dead_group_list = uct_dead_group_list;
1172         e->done = uct_done;
1173         e->data = u;
1174         if (u->slave)
1175                 e->notify = uct_notify;
1176
1177         const char banner[] = "If you believe you have won but I am still playing, "
1178                 "please help me understand by capturing all dead stones. "
1179                 "Anyone can send me 'winrate' in private chat to get my assessment of the position.";
1180         if (!u->banner) u->banner = "";
1181         e->comment = malloc2(sizeof(banner) + strlen(u->banner) + 1);
1182         sprintf(e->comment, "%s %s", banner, u->banner);
1183
1184         return e;
1185 }