uct/uct.c

   1 #include <assert.h>
   2 #include <pthread.h>
   3 #include <signal.h>
   4 #include <stdio.h>
   5 #include <stdlib.h>
   6 #include <string.h>
   7
   8 #define DEBUG
   9
  10 #include "debug.h"
  11 #include "board.h"
  12 #include "move.h"
  13 #include "playout.h"
  14 #include "playout/moggy.h"
  15 #include "playout/light.h"
  16 #include "random.h"
  17 #include "tactics.h"
  18 #include "uct/internal.h"
  19 #include "uct/prior.h"
  20 #include "uct/tree.h"
  21 #include "uct/uct.h"
  22
  23 struct uct_policy *policy_ucb1_init(struct uct *u, char *arg);
  24 struct uct_policy *policy_ucb1amaf_init(struct uct *u, char *arg);
  25
  26
  27 #define MC_GAMES        80000
  28 #define MC_GAMELEN      MAX_GAMELEN
  29
  30
  31 static bool
  32 can_pass(struct board *b, enum stone color)
  33 {
  34         float score = board_official_score(b);
  35         if (color == S_BLACK)
  36                 score = -score;
  37         //fprintf(stderr, "%d score %f\n", color, score);
  38         return (score > 0);
  39 }
  40
  41 static float
  42 get_extra_komi(struct uct *u, struct board *b, enum stone player_color)
  43 {
  44         float extra_komi = board_effective_handicap(b) * (u->dynkomi - b->moves) / u->dynkomi;
  45         if (player_color == S_WHITE)
  46                 extra_komi *= -1;
  47         return extra_komi;
  48 }
  49
  50 static void
  51 progress_status(struct uct *u, struct tree *t, enum stone color, int playouts)
  52 {
  53         if (!UDEBUGL(0))
  54                 return;
  55
  56         /* Best move */
  57         struct tree_node *best = u->policy->choose(u->policy, t->root, t->board, color);
  58         if (!best) {
  59                 fprintf(stderr, "... No moves left\n");
  60                 return;
  61         }
  62         fprintf(stderr, "[%d] ", playouts);
  63         fprintf(stderr, "best %f ", tree_node_get_value(t, best, u, 1));
  64
  65         /* Max depth */
  66         fprintf(stderr, "deepest % 2d ", t->max_depth - t->root->depth);
  67
  68         /* Best sequence */
  69         fprintf(stderr, "| seq ");
  70         for (int depth = 0; depth < 6; depth++) {
  71                 if (best && best->u.playouts >= 25) {
  72                         fprintf(stderr, "%3s ", coord2sstr(best->coord, t->board));
  73                         best = u->policy->choose(u->policy, best, t->board, color);
  74                 } else {
  75                         fprintf(stderr, "    ");
  76                 }
  77         }
  78
  79         /* Best candidates */
  80         fprintf(stderr, "| can ");
  81         int cans = 4;
  82         struct tree_node *can[cans];
  83         memset(can, 0, sizeof(can));
  84         best = t->root->children;
  85         while (best) {
  86                 int c = 0;
  87                 while ((!can[c] || best->u.playouts > can[c]->u.playouts) && ++c < cans);
  88                 for (int d = 0; d < c; d++) can[d] = can[d + 1];
  89                 if (c > 0) can[c - 1] = best;
  90                 best = best->sibling;
  91         }
  92         while (--cans >= 0) {
  93                 if (can[cans]) {
  94                         fprintf(stderr, "%3s(%.3f) ",
  95                                 coord2sstr(can[cans]->coord, t->board),
  96                                 tree_node_get_value(t, can[cans], u, 1));
  97                 } else {
  98                         fprintf(stderr, "           ");
  99                 }
 100         }
 101
 102         fprintf(stderr, "\n");
 103 }
 104
 105
 106 static int
 107 uct_leaf_node(struct uct *u, struct board *b, enum stone player_color,
 108               struct playout_amafmap *amaf,
 109               struct tree *t, struct tree_node *n, enum stone node_color,
 110               char *spaces)
 111 {
 112         enum stone next_color = stone_other(node_color);
 113         int parity = (next_color == player_color ? 1 : -1);
 114         if (n->u.playouts >= u->expand_p) {
 115                 // fprintf(stderr, "expanding %s (%p ^-%p)\n", coord2sstr(n->coord, b), n, n->parent);
 116                 tree_expand_node(t, n, b, next_color, u->radar_d, u, parity);
 117         }
 118         if (UDEBUGL(7))
 119                 fprintf(stderr, "%s*-- UCT playout #%d start [%s] %f\n",
 120                         spaces, n->u.playouts, coord2sstr(n->coord, t->board),
 121                         tree_node_get_value(t, n, u, parity));
 122
 123         int result = play_random_game(b, next_color, u->gamelen, u->playout_amaf ? amaf : NULL, NULL, u->playout);
 124         if (next_color == S_WHITE) {
 125                 /* We need the result from black's perspective. */
 126                 result = - result;
 127         }
 128         if (UDEBUGL(7))
 129                 fprintf(stderr, "%s -- [%d..%d] %s random playout result %d\n",
 130                         spaces, player_color, next_color, coord2sstr(n->coord, t->board), result);
 131
 132         return result;
 133 }
 134
 135 static int
 136 uct_playout(struct uct *u, struct board *b, enum stone player_color, struct tree *t)
 137 {
 138         struct board b2;
 139         board_copy(&b2, b);
 140
 141         struct playout_amafmap *amaf = NULL;
 142         if (u->policy->wants_amaf) {
 143                 amaf = calloc(1, sizeof(*amaf));
 144                 amaf->map = calloc(board_size2(&b2) + 1, sizeof(*amaf->map));
 145                 amaf->map++; // -1 is pass
 146         }
 147
 148         /* Walk the tree until we find a leaf, then expand it and do
 149          * a random playout. */
 150         struct tree_node *n = t->root;
 151         enum stone node_color = stone_other(player_color);
 152         assert(node_color == t->root_color);
 153
 154         int result;
 155         int pass_limit = (board_size(&b2) - 2) * (board_size(&b2) - 2) / 2;
 156         int passes = is_pass(b->last_move.coord);
 157
 158         /* debug */
 159         int depth = 0;
 160         static char spaces[] = "\0                                                      ";
 161         /* /debug */
 162         if (UDEBUGL(8))
 163                 fprintf(stderr, "--- UCT walk with color %d\n", player_color);
 164
 165         while (!tree_leaf_node(n) && passes < 2) {
 166                 spaces[depth++] = ' '; spaces[depth] = 0;
 167
 168                 /* Parity is chosen already according to the child color, since
 169                  * it is applied to children. */
 170                 node_color = stone_other(node_color);
 171                 int parity = (node_color == player_color ? 1 : -1);
 172                 n = u->policy->descend(u->policy, t, n, parity, pass_limit);
 173
 174                 assert(n == t->root || n->parent);
 175                 if (UDEBUGL(7))
 176                         fprintf(stderr, "%s+-- UCT sent us to [%s:%d] %f\n",
 177                                 spaces, coord2sstr(n->coord, t->board), n->coord,
 178                                 tree_node_get_value(t, n, u, parity));
 179
 180                 assert(n->coord >= -1);
 181                 if (amaf && !is_pass(n->coord)) {
 182                         if (amaf->map[n->coord] == S_NONE || amaf->map[n->coord] == node_color) {
 183                                 amaf->map[n->coord] = node_color;
 184                         } else { // XXX: Respect amaf->record_nakade
 185                                 amaf_op(amaf->map[n->coord], +);
 186                         }
 187                         amaf->game[amaf->gamelen].coord = n->coord;
 188                         amaf->game[amaf->gamelen].color = node_color;
 189                         amaf->gamelen++;
 190                         assert(amaf->gamelen < sizeof(amaf->game) / sizeof(amaf->game[0]));
 191                 }
 192
 193                 struct move m = { n->coord, node_color };
 194                 int res = board_play(&b2, &m);
 195
 196                 if (res < 0 || (!is_pass(m.coord) && !group_at(&b2, m.coord)) /* suicide */
 197                     || b2.superko_violation) {
 198                         if (UDEBUGL(3)) {
 199                                 for (struct tree_node *ni = n; ni; ni = ni->parent)
 200                                         fprintf(stderr, "%s<%lld> ", coord2sstr(ni->coord, t->board), ni->hash);
 201                                 fprintf(stderr, "deleting invalid %s node %d,%d res %d group %d spk %d\n",
 202                                         stone2str(node_color), coord_x(n->coord,b), coord_y(n->coord,b),
 203                                         res, group_at(&b2, m.coord), b2.superko_violation);
 204                         }
 205                         tree_delete_node(t, n);
 206                         result = 0;
 207                         goto end;
 208                 }
 209
 210                 if (is_pass(n->coord))
 211                         passes++;
 212                 else
 213                         passes = 0;
 214         }
 215
 216         if (amaf) {
 217                 amaf->game_baselen = amaf->gamelen;
 218                 amaf->record_nakade = u->playout_amaf_nakade;
 219         }
 220
 221         if (passes >= 2) {
 222                 float score = board_official_score(&b2);
 223                 /* Result from black's perspective (no matter who
 224                  * the player; black's perspective is always
 225                  * what the tree stores. */
 226                 result = - (score * 2);
 227
 228                 if (UDEBUGL(5))
 229                         fprintf(stderr, "[%d..%d] %s p-p scoring playout result %d (W %f)\n",
 230                                 player_color, node_color, coord2sstr(n->coord, t->board), result, score);
 231                 if (UDEBUGL(6))
 232                         board_print(&b2, stderr);
 233
 234         } else { assert(tree_leaf_node(n));
 235                 if (u->dynkomi > b2.moves)
 236                         b2.komi += get_extra_komi(u, &b2, player_color);
 237                 result = uct_leaf_node(u, &b2, player_color, amaf, t, n, node_color, spaces);
 238         }
 239
 240         if (amaf && u->playout_amaf_cutoff) {
 241                 int cutoff = amaf->game_baselen;
 242                 cutoff += (amaf->gamelen - amaf->game_baselen) * u->playout_amaf_cutoff / 100;
 243                 /* Now, reconstruct the amaf map. */
 244                 memset(amaf->map, 0, board_size2(&b2) * sizeof(*amaf->map));
 245                 for (int i = 0; i < cutoff; i++) {
 246                         coord_t coord = amaf->game[i].coord;
 247                         enum stone color = amaf->game[i].color;
 248                         if (amaf->map[coord] == S_NONE || amaf->map[coord] == color) {
 249                                 amaf->map[coord] = color;
 250                         /* Nakade always recorded for in-tree part */
 251                         } else if (amaf->record_nakade || i <= amaf->game_baselen) {
 252                                 amaf_op(amaf->map[n->coord], +);
 253                         }
 254                 }
 255         }
 256
 257         assert(n == t->root || n->parent);
 258         if (result != 0) {
 259                 float rval = result > 0;
 260                 if (u->val_scale) {
 261                         float sval = (float) abs(result) / u->val_points;
 262                         sval = sval > 1 ? 1 : sval;
 263                         if (result < 0) sval = 1 - sval;
 264                         rval = (1 - u->val_scale) * rval + u->val_scale * sval;
 265                         // fprintf(stderr, "score %d => sval %f, rval %f\n", result, sval, rval);
 266                 }
 267                 u->policy->update(u->policy, t, n, node_color, player_color, amaf, rval);
 268         }
 269
 270 end:
 271         if (amaf) {
 272                 free(amaf->map - 1);
 273                 free(amaf);
 274         }
 275         board_done_noalloc(&b2);
 276         return result;
 277 }
 278
 279 static void
 280 prepare_move(struct engine *e, struct board *b, enum stone color, coord_t promote)
 281 {
 282         struct uct *u = e->data;
 283
 284         if (u->t && (!b->moves || color != stone_other(u->t->root_color))) {
 285                 /* Stale state from last game */
 286                 tree_done(u->t);
 287                 u->t = NULL;
 288         }
 289
 290         if (!u->t) {
 291                 u->t = tree_init(b, color);
 292                 if (u->force_seed)
 293                         fast_srandom(u->force_seed);
 294                 if (UDEBUGL(0))
 295                         fprintf(stderr, "Fresh board with random seed %lu\n", fast_getseed());
 296                 //board_print(b, stderr);
 297                 if (!u->no_book && b->moves < 2)
 298                         tree_load(u->t, b);
 299         }
 300
 301         /* XXX: We hope that the opponent didn't suddenly play
 302          * several moves in the row. */
 303         if (!is_resign(promote) && !tree_promote_at(u->t, b, promote)) {
 304                 if (UDEBUGL(2))
 305                         fprintf(stderr, "<cannot find node to promote>\n");
 306                 /* Reset tree */
 307                 tree_done(u->t);
 308                 u->t = tree_init(b, color);
 309         }
 310
 311         if (u->dynkomi)
 312                 u->t->extra_komi = get_extra_komi(u, b, color);
 313 }
 314
 315 /* Set in main thread in case the playouts should stop. */
 316 static volatile sig_atomic_t halt = 0;
 317
 318 static int
 319 uct_playouts(struct uct *u, struct board *b, enum stone color, struct tree *t)
 320 {
 321         int i, games = u->games;
 322         if (t->root->children)
 323                 games -= t->root->u.playouts / 1.5;
 324         /* else this is highly read-out but dead-end branch of opening book;
 325          * we need to start from scratch; XXX: Maybe actually base the readout
 326          * count based on number of playouts of best node? */
 327         for (i = 0; i < games; i++) {
 328                 int result = uct_playout(u, b, color, t);
 329                 if (result == 0) {
 330                         /* Tree descent has hit invalid move. */
 331                         continue;
 332                 }
 333
 334                 if (i > 0 && !(i % 10000)) {
 335                         progress_status(u, t, color, i);
 336                 }
 337
 338                 if (i > 0 && !(i % 500)) {
 339                         struct tree_node *best = u->policy->choose(u->policy, t->root, b, color);
 340                         if (best && ((best->u.playouts >= 5000 && tree_node_get_value(t, best, u, 1) >= u->loss_threshold)
 341                                      || (best->u.playouts >= 500 && tree_node_get_value(t, best, u, 1) >= 0.95)))
 342                                 break;
 343                 }
 344
 345                 if (halt) {
 346                         if (UDEBUGL(2))
 347                                 fprintf(stderr, "<halting early, %d games skipped>\n", games - i);
 348                         break;
 349                 }
 350         }
 351
 352         progress_status(u, t, color, i);
 353         if (UDEBUGL(3))
 354                 tree_dump(t, u->dumpthres);
 355         return i;
 356 }
 357
 358 static pthread_mutex_t finish_mutex = PTHREAD_MUTEX_INITIALIZER;
 359 static pthread_cond_t finish_cond = PTHREAD_COND_INITIALIZER;
 360 static volatile int finish_thread;
 361 static pthread_mutex_t finish_serializer = PTHREAD_MUTEX_INITIALIZER;
 362
 363 struct spawn_ctx {
 364         int tid;
 365         struct uct *u;
 366         struct board *b;
 367         enum stone color;
 368         struct tree *t;
 369         unsigned long seed;
 370         int games;
 371 };
 372
 373 static void *
 374 spawn_helper(void *ctx_)
 375 {
 376         struct spawn_ctx *ctx = ctx_;
 377         /* Setup */
 378         fast_srandom(ctx->seed);
 379         /* Run */
 380         ctx->games = uct_playouts(ctx->u, ctx->b, ctx->color, ctx->t);
 381         /* Finish */
 382         pthread_mutex_lock(&finish_serializer);
 383         pthread_mutex_lock(&finish_mutex);
 384         finish_thread = ctx->tid;
 385         pthread_cond_signal(&finish_cond);
 386         pthread_mutex_unlock(&finish_mutex);
 387         return ctx;
 388 }
 389
 390 static void
 391 uct_notify_play(struct engine *e, struct board *b, struct move *m)
 392 {
 393         prepare_move(e, b, m->color, m->coord);
 394 }
 395
 396 static coord_t *
 397 uct_genmove(struct engine *e, struct board *b, enum stone color)
 398 {
 399         struct uct *u = e->data;
 400
 401         /* Seed the tree. */
 402         prepare_move(e, b, color, resign);
 403
 404         if (b->superko_violation) {
 405                 fprintf(stderr, "!!! WARNING: SUPERKO VIOLATION OCCURED BEFORE THIS MOVE\n");
 406                 fprintf(stderr, "Maybe you play with situational instead of positional superko?\n");
 407                 fprintf(stderr, "I'm going to ignore the violation, but note that I may miss\n");
 408                 fprintf(stderr, "some moves valid under this ruleset because of this.\n");
 409                 b->superko_violation = false;
 410         }
 411
 412         /* If the opponent just passes and we win counting, just
 413          * pass as well. */
 414         if (b->moves > 1 && is_pass(b->last_move.coord) && can_pass(b, color))
 415                 return coord_copy(pass);
 416
 417         int played_games = 0;
 418         if (!u->threads) {
 419                 played_games = uct_playouts(u, b, color, u->t);
 420         } else {
 421                 pthread_t threads[u->threads];
 422                 int joined = 0;
 423                 halt = 0;
 424                 pthread_mutex_lock(&finish_mutex);
 425                 /* Spawn threads... */
 426                 for (int ti = 0; ti < u->threads; ti++) {
 427                         struct spawn_ctx *ctx = malloc(sizeof(*ctx));
 428                         ctx->u = u; ctx->b = b; ctx->color = color;
 429                         ctx->t = tree_copy(u->t); ctx->tid = ti;
 430                         ctx->seed = fast_random(65536) + ti;
 431                         pthread_create(&threads[ti], NULL, spawn_helper, ctx);
 432                         if (UDEBUGL(2))
 433                                 fprintf(stderr, "Spawned thread %d\n", ti);
 434                 }
 435                 /* ...and collect them back: */
 436                 while (joined < u->threads) {
 437                         /* Wait for some thread to finish... */
 438                         pthread_cond_wait(&finish_cond, &finish_mutex);
 439                         /* ...and gather its remnants. */
 440                         struct spawn_ctx *ctx;
 441                         pthread_join(threads[finish_thread], (void **) &ctx);
 442                         played_games += ctx->games;
 443                         joined++;
 444                         tree_merge(u->t, ctx->t);
 445                         tree_done(ctx->t);
 446                         free(ctx);
 447                         if (UDEBUGL(2))
 448                                 fprintf(stderr, "Joined thread %d\n", finish_thread);
 449                         /* Do not get stalled by slow threads. */
 450                         if (joined >= u->threads / 2)
 451                                 halt = 1;
 452                         pthread_mutex_unlock(&finish_serializer);
 453                 }
 454                 pthread_mutex_unlock(&finish_mutex);
 455
 456                 tree_normalize(u->t, u->threads);
 457         }
 458
 459         if (UDEBUGL(2))
 460                 tree_dump(u->t, u->dumpthres);
 461
 462         struct tree_node *best = u->policy->choose(u->policy, u->t->root, b, color);
 463         if (!best) {
 464                 tree_done(u->t); u->t = NULL;
 465                 return coord_copy(pass);
 466         }
 467         if (UDEBUGL(0))
 468                 progress_status(u, u->t, color, played_games);
 469         if (UDEBUGL(1))
 470                 fprintf(stderr, "*** WINNER is %s (%d,%d) with score %1.4f (%d/%d:%d games)\n",
 471                         coord2sstr(best->coord, b), coord_x(best->coord, b), coord_y(best->coord, b),
 472                         tree_node_get_value(u->t, best, u, 1),
 473                         best->u.playouts, u->t->root->u.playouts, played_games);
 474         if (tree_node_get_value(u->t, best, u, 1) < u->resign_ratio && !is_pass(best->coord)) {
 475                 tree_done(u->t); u->t = NULL;
 476                 return coord_copy(resign);
 477         }
 478         tree_promote_node(u->t, best);
 479         return coord_copy(best->coord);
 480 }
 481
 482 bool
 483 uct_genbook(struct engine *e, struct board *b, enum stone color)
 484 {
 485         struct uct *u = e->data;
 486         u->t = tree_init(b, color);
 487         tree_load(u->t, b);
 488
 489         int i;
 490         for (i = 0; i < u->games; i++) {
 491                 int result = uct_playout(u, b, color, u->t);
 492                 if (result == 0) {
 493                         /* Tree descent has hit invalid move. */
 494                         continue;
 495                 }
 496
 497                 if (i > 0 && !(i % 10000)) {
 498                         progress_status(u, u->t, color, i);
 499                 }
 500         }
 501         progress_status(u, u->t, color, i);
 502
 503         tree_save(u->t, b, u->games / 100);
 504
 505         tree_done(u->t);
 506
 507         return true;
 508 }
 509
 510 void
 511 uct_dumpbook(struct engine *e, struct board *b, enum stone color)
 512 {
 513         struct uct *u = e->data;
 514         u->t = tree_init(b, color);
 515         tree_load(u->t, b);
 516         tree_dump(u->t, 0);
 517         tree_done(u->t);
 518 }
 519
 520
 521 struct uct *
 522 uct_state_init(char *arg)
 523 {
 524         struct uct *u = calloc(1, sizeof(struct uct));
 525
 526         u->debug_level = 1;
 527         u->games = MC_GAMES;
 528         u->gamelen = MC_GAMELEN;
 529         u->expand_p = 2;
 530         u->dumpthres = 1000;
 531         u->playout_amaf = true;
 532         u->playout_amaf_nakade = false;
 533         u->amaf_prior = true;
 534
 535         if (arg) {
 536                 char *optspec, *next = arg;
 537                 while (*next) {
 538                         optspec = next;
 539                         next += strcspn(next, ",");
 540                         if (*next) { *next++ = 0; } else { *next = 0; }
 541
 542                         char *optname = optspec;
 543                         char *optval = strchr(optspec, '=');
 544                         if (optval) *optval++ = 0;
 545
 546                         if (!strcasecmp(optname, "debug")) {
 547                                 if (optval)
 548                                         u->debug_level = atoi(optval);
 549                                 else
 550                                         u->debug_level++;
 551                         } else if (!strcasecmp(optname, "games") && optval) {
 552                                 u->games = atoi(optval);
 553                         } else if (!strcasecmp(optname, "gamelen") && optval) {
 554                                 u->gamelen = atoi(optval);
 555                         } else if (!strcasecmp(optname, "expand_p") && optval) {
 556                                 u->expand_p = atoi(optval);
 557                         } else if (!strcasecmp(optname, "radar_d") && optval) {
 558                                 /* For 19x19, it is good idea to set this to 3. */
 559                                 u->radar_d = atoi(optval);
 560                         } else if (!strcasecmp(optname, "dumpthres") && optval) {
 561                                 u->dumpthres = atoi(optval);
 562                         } else if (!strcasecmp(optname, "playout_amaf")) {
 563                                 /* Whether to include random playout moves in
 564                                  * AMAF as well. (Otherwise, only tree moves
 565                                  * are included in AMAF. Of course makes sense
 566                                  * only in connection with an AMAF policy.) */
 567                                 /* with-without: 55.5% (+-4.1) */
 568                                 if (optval && *optval == '0')
 569                                         u->playout_amaf = false;
 570                                 else
 571                                         u->playout_amaf = true;
 572                         } else if (!strcasecmp(optname, "playout_amaf_nakade")) {
 573                                 /* Whether to include nakade moves from playouts
 574                                  * in the AMAF statistics; this tends to nullify
 575                                  * the playout_amaf effect by adding too much
 576                                  * noise. */
 577                                 if (optval && *optval == '0')
 578                                         u->playout_amaf_nakade = false;
 579                                 else
 580                                         u->playout_amaf_nakade = true;
 581                         } else if (!strcasecmp(optname, "playout_amaf_cutoff") && optval) {
 582                                 /* Keep only first N% of playout stage AMAF
 583                                  * information. */
 584                                 u->playout_amaf_cutoff = atoi(optval);
 585                         } else if (!strcasecmp(optname, "policy") && optval) {
 586                                 char *policyarg = strchr(optval, ':');
 587                                 if (policyarg)
 588                                         *policyarg++ = 0;
 589                                 if (!strcasecmp(optval, "ucb1")) {
 590                                         u->policy = policy_ucb1_init(u, policyarg);
 591                                 } else if (!strcasecmp(optval, "ucb1amaf")) {
 592                                         u->policy = policy_ucb1amaf_init(u, policyarg);
 593                                 } else {
 594                                         fprintf(stderr, "UCT: Invalid tree policy %s\n", optval);
 595                                 }
 596                         } else if (!strcasecmp(optname, "playout") && optval) {
 597                                 char *playoutarg = strchr(optval, ':');
 598                                 if (playoutarg)
 599                                         *playoutarg++ = 0;
 600                                 if (!strcasecmp(optval, "moggy")) {
 601                                         u->playout = playout_moggy_init(playoutarg);
 602                                 } else if (!strcasecmp(optval, "light")) {
 603                                         u->playout = playout_light_init(playoutarg);
 604                                 } else {
 605                                         fprintf(stderr, "UCT: Invalid playout policy %s\n", optval);
 606                                 }
 607                         } else if (!strcasecmp(optname, "prior") && optval) {
 608                                 u->prior = uct_prior_init(optval);
 609                         } else if (!strcasecmp(optname, "amaf_prior") && optval) {
 610                                 u->amaf_prior = atoi(optval);
 611                         } else if (!strcasecmp(optname, "threads") && optval) {
 612                                 u->threads = atoi(optval);
 613                         } else if (!strcasecmp(optname, "force_seed") && optval) {
 614                                 u->force_seed = atoi(optval);
 615                         } else if (!strcasecmp(optname, "no_book")) {
 616                                 u->no_book = true;
 617                         } else if (!strcasecmp(optname, "dynkomi")) {
 618                                 /* Dynamic komi in handicap game; linearly
 619                                  * decreases to basic settings until move
 620                                  * #optval. */
 621                                 u->dynkomi = optval ? atoi(optval) : 150;
 622                         } else if (!strcasecmp(optname, "val_scale") && optval) {
 623                                 /* How much of the game result value should be
 624                                  * influenced by win size. */
 625                                 u->val_scale = atof(optval);
 626                         } else if (!strcasecmp(optname, "val_points") && optval) {
 627                                 /* Maximum size of win to be scaled into game
 628                                  * result value. */
 629                                 u->val_points = atoi(optval) * 2; // result values are doubled
 630                         } else {
 631                                 fprintf(stderr, "uct: Invalid engine argument %s or missing value\n", optname);
 632                                 exit(1);
 633                         }
 634                 }
 635         }
 636
 637         u->resign_ratio = 0.2; /* Resign when most games are lost. */
 638         u->loss_threshold = 0.85; /* Stop reading if after at least 5000 playouts this is best value. */
 639         if (!u->policy)
 640                 u->policy = policy_ucb1amaf_init(u, NULL);
 641
 642         if (!u->prior)
 643                 u->prior = uct_prior_init(NULL);
 644
 645         if (!u->playout)
 646                 u->playout = playout_moggy_init(NULL);
 647         u->playout->debug_level = u->debug_level;
 648
 649         return u;
 650 }
 651
 652
 653 struct engine *
 654 engine_uct_init(char *arg)
 655 {
 656         struct uct *u = uct_state_init(arg);
 657         struct engine *e = calloc(1, sizeof(struct engine));
 658         e->name = "UCT Engine";
 659         e->comment = "I'm playing UCT. When we both pass, I will consider all the stones on the board alive. If you are reading this, write 'yes'. Please capture all dead stones before passing; it will not cost you points (area scoring is used).";
 660         e->genmove = uct_genmove;
 661         e->notify_play = uct_notify_play;
 662         e->data = u;
 663
 664         return e;
 665 }