uct/tree.c

   1 #include <assert.h>
   2 #include <math.h>
   3 #include <stddef.h>
   4 #include <stdint.h>
   5 #include <stdio.h>
   6 #include <stdlib.h>
   7 #include <string.h>
   8
   9 #include "board.h"
  10 #include "debug.h"
  11 #include "engine.h"
  12 #include "move.h"
  13 #include "playout.h"
  14 #include "uct/internal.h"
  15 #include "uct/tree.h"
  16
  17
  18 static struct tree_node *
  19 tree_init_node(struct tree *t, coord_t coord, int depth)
  20 {
  21         struct tree_node *n = calloc(1, sizeof(*n));
  22         n->coord = coord;
  23         n->depth = depth;
  24         if (depth > t->max_depth)
  25                 t->max_depth = depth;
  26         return n;
  27 }
  28
  29 struct tree *
  30 tree_init(struct board *board, enum stone color)
  31 {
  32         struct tree *t = calloc(1, sizeof(*t));
  33         t->board = board;
  34         /* The root PASS move is only virtual, we never play it. */
  35         t->root = tree_init_node(t, pass, 0);
  36         t->root_symmetry = board->symmetry;
  37         return t;
  38 }
  39
  40
  41 static void
  42 tree_done_node(struct tree *t, struct tree_node *n)
  43 {
  44         struct tree_node *ni = n->children;
  45         while (ni) {
  46                 struct tree_node *nj = ni->sibling;
  47                 tree_done_node(t, ni);
  48                 ni = nj;
  49         }
  50         free(n);
  51 }
  52
  53 void
  54 tree_done(struct tree *t)
  55 {
  56         tree_done_node(t, t->root);
  57         free(t);
  58 }
  59
  60
  61 static void
  62 tree_node_dump(struct tree *tree, struct tree_node *node, int l, int thres)
  63 {
  64         for (int i = 0; i < l; i++) fputc(' ', stderr);
  65         int children = 0;
  66         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
  67                 children++;
  68         fprintf(stderr, "[%s] %f (%d/%d playouts [prior %d/%d amaf %d/%d]; hints %x; %d children)\n", coord2sstr(node->coord, tree->board), node->u.value, node->u.wins, node->u.playouts, node->prior.wins, node->prior.playouts, node->amaf.wins, node->amaf.playouts, node->hints, children);
  69
  70         /* Print nodes sorted by #playouts. */
  71
  72         struct tree_node *nbox[1000]; int nboxl = 0;
  73         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
  74                 if (ni->u.playouts > thres)
  75                         nbox[nboxl++] = ni;
  76
  77         while (true) {
  78                 int best = -1;
  79                 for (int i = 0; i < nboxl; i++)
  80                         if (nbox[i] && (best < 0 || nbox[i]->u.playouts > nbox[best]->u.playouts))
  81                                 best = i;
  82                 if (best < 0)
  83                         break;
  84                 tree_node_dump(tree, nbox[best], l + 1, /* node->u.value < 0.1 ? 0 : */ thres);
  85                 nbox[best] = NULL;
  86         }
  87 }
  88
  89 void
  90 tree_dump(struct tree *tree, int thres)
  91 {
  92         if (thres && tree->root->u.playouts / thres > 100) {
  93                 /* Be a bit sensible about this; the opening book can create
  94                  * huge dumps at first. */
  95                 thres = tree->root->u.playouts / 100 * (thres < 1000 ? 1 : thres / 1000);
  96         }
  97         tree_node_dump(tree, tree->root, 0, thres);
  98 }
  99
 100
 101 static char *
 102 tree_book_name(struct board *b)
 103 {
 104         static char buf[256];
 105         if (b->handicap > 0) {
 106                 sprintf(buf, "uctbook-%d-%02.01f-h%d.pachitree", b->size - 2, b->komi, b->handicap);
 107         } else {
 108                 sprintf(buf, "uctbook-%d-%02.01f.pachitree", b->size - 2, b->komi);
 109         }
 110         return buf;
 111 }
 112
 113 static void
 114 tree_node_save(FILE *f, struct tree_node *node, int thres)
 115 {
 116         fputc(1, f);
 117         fwrite(((void *) node) + offsetof(struct tree_node, depth),
 118                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 119                1, f);
 120
 121         if (node->u.playouts >= thres)
 122                 for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 123                         tree_node_save(f, ni, thres);
 124
 125         fputc(0, f);
 126 }
 127
 128 void
 129 tree_save(struct tree *tree, struct board *b, int thres)
 130 {
 131         char *filename = tree_book_name(b);
 132         FILE *f = fopen(filename, "wb");
 133         if (!f) {
 134                 perror("fopen");
 135                 return;
 136         }
 137         tree_node_save(f, tree->root, thres);
 138         fputc(0, f);
 139         fclose(f);
 140 }
 141
 142
 143 void
 144 tree_node_load(FILE *f, struct tree_node *node, int *num, bool invert)
 145 {
 146         (*num)++;
 147
 148         fread(((void *) node) + offsetof(struct tree_node, depth),
 149                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 150                1, f);
 151
 152         /* Keep values in sane scale, otherwise we start overflowing.
 153          * We may go slow here but we must be careful about not getting
 154          * too huge integers.*/
 155 #define MAX_PLAYOUTS    10000000
 156         if (node->u.playouts > MAX_PLAYOUTS) {
 157                 int over = node->u.playouts - MAX_PLAYOUTS;
 158                 node->u.wins -= ((double) node->u.wins / node->u.playouts) * over;
 159                 node->u.playouts = MAX_PLAYOUTS;
 160         }
 161         if (node->amaf.playouts > MAX_PLAYOUTS) {
 162                 int over = node->amaf.playouts - MAX_PLAYOUTS;
 163                 node->amaf.wins -= ((double) node->amaf.wins / node->amaf.playouts) * over;
 164                 node->amaf.playouts = MAX_PLAYOUTS;
 165         }
 166
 167         if (invert) {
 168                 node->u.wins = node->u.playouts - node->u.wins;
 169                 node->u.value = 1 - node->u.value;
 170                 node->amaf.wins = node->amaf.playouts - node->amaf.wins;
 171                 node->amaf.value = 1 - node->amaf.value;
 172                 node->prior.wins = node->prior.playouts - node->prior.wins;
 173                 node->prior.value = 1 - node->prior.value;
 174         }
 175
 176         struct tree_node *ni = NULL, *ni_prev = NULL;
 177         while (fgetc(f)) {
 178                 ni_prev = ni; ni = calloc(1, sizeof(*ni));
 179                 if (!node->children)
 180                         node->children = ni;
 181                 else
 182                         ni_prev->sibling = ni;
 183                 ni->parent = node;
 184                 tree_node_load(f, ni, num, invert);
 185         }
 186 }
 187
 188 void
 189 tree_load(struct tree *tree, struct board *b, enum stone color)
 190 {
 191         char *filename = tree_book_name(b);
 192         FILE *f = fopen(filename, "rb");
 193         if (!f)
 194                 return;
 195
 196         fprintf(stderr, "Loading opening book %s...\n", filename);
 197
 198         int num = 0;
 199         if (fgetc(f))
 200                 tree_node_load(f, tree->root, &num, color != S_BLACK);
 201         fprintf(stderr, "Loaded %d nodes.\n", num);
 202
 203         fclose(f);
 204 }
 205
 206
 207 static struct tree_node *
 208 tree_node_copy(struct tree_node *node)
 209 {
 210         struct tree_node *n2 = malloc(sizeof(*n2));
 211         *n2 = *node;
 212         if (!node->children)
 213                 return n2;
 214         struct tree_node *ni = node->children;
 215         struct tree_node *ni2 = tree_node_copy(ni);
 216         n2->children = ni2; ni2->parent = n2;
 217         while ((ni = ni->sibling)) {
 218                 ni2->sibling = tree_node_copy(ni);
 219                 ni2 = ni2->sibling; ni2->parent = n2;
 220         }
 221         return n2;
 222 }
 223
 224 struct tree *
 225 tree_copy(struct tree *tree)
 226 {
 227         struct tree *t2 = malloc(sizeof(*t2));
 228         *t2 = *tree;
 229         t2->root = tree_node_copy(tree->root);
 230         return t2;
 231 }
 232
 233
 234 static void
 235 tree_node_merge(struct tree_node *dest, struct tree_node *src)
 236 {
 237         dest->hints |= src->hints;
 238
 239         /* Merge the children, both are coord-sorted lists. */
 240         struct tree_node *di = dest->children, *dip = NULL;
 241         struct tree_node *si = src->children, *sip = NULL;
 242         while (di && si) {
 243                 if (di->coord != si->coord) {
 244                         /* src has some extra items or misses di */
 245                         struct tree_node *si2 = si->sibling;
 246                         while (si2 && di->coord != si2->coord) {
 247                                 si2 = si2->sibling;
 248                         }
 249                         if (!si2)
 250                                 goto next_di; /* src misses di, move on */
 251                         /* chain the extra [si,si2) items before di */
 252                         if (dip)
 253                                 dip->sibling = si;
 254                         else
 255                                 dest->children = si;
 256                         while (si->sibling != si2) {
 257                                 si->parent = dest;
 258                                 si = si->sibling;
 259                         }
 260                         si->sibling = di;
 261                         si = si2;
 262                         if (sip)
 263                                 sip->sibling = si;
 264                         else
 265                                 src->children = si;
 266                 }
 267                 /* Matching nodes - recurse... */
 268                 tree_node_merge(di, si);
 269                 /* ...and move on. */
 270                 sip = si; si = si->sibling;
 271 next_di:
 272                 dip = di; di = di->sibling;
 273         }
 274         if (si) {
 275                 if (dip)
 276                         dip->sibling = si;
 277                 else
 278                         dest->children = si;
 279                 while (si) {
 280                         si->parent = dest;
 281                         si = si->sibling;
 282                 }
 283                 if (sip)
 284                         sip->sibling = NULL;
 285                 else
 286                         src->children = NULL;
 287         }
 288
 289         /* In case of prior playouts, we do not want to accumulate them
 290          * over merges - they remain static after setup. However, different
 291          * trees may have different priors non-deterministically. We just
 292          * take the average. */
 293         if (dest->prior.playouts != src->prior.playouts
 294             || dest->prior.wins != src->prior.wins) {
 295                 dest->prior.playouts = (dest->prior.playouts + src->prior.playouts) / 2;
 296                 dest->prior.wins = (dest->prior.wins + src->prior.wins) / 2;
 297                 if (dest->prior.playouts)
 298                         dest->prior.value = dest->prior.wins / dest->prior.playouts;
 299         }
 300
 301         dest->amaf.playouts += src->amaf.playouts;
 302         dest->amaf.wins += src->amaf.wins;
 303         if (dest->amaf.playouts)
 304                 dest->amaf.value = dest->amaf.wins / dest->amaf.playouts;
 305
 306         dest->u.playouts += src->u.playouts;
 307         dest->u.wins += src->u.wins;
 308         if (dest->prior.playouts + dest->amaf.playouts + dest->u.playouts)
 309                 tree_update_node_value(dest);
 310 }
 311
 312 /* Merge two trees built upon the same board. Note that the operation is
 313  * destructive on src. */
 314 void
 315 tree_merge(struct tree *dest, struct tree *src)
 316 {
 317         if (src->max_depth > dest->max_depth)
 318                 dest->max_depth = src->max_depth;
 319         tree_node_merge(dest->root, src->root);
 320 }
 321
 322
 323 /* Tree symmetry: When possible, we will localize the tree to a single part
 324  * of the board in tree_expand_node() and possibly flip along symmetry axes
 325  * to another part of the board in tree_promote_at(). We follow b->symmetry
 326  * guidelines here. */
 327
 328
 329 void
 330 tree_expand_node(struct tree *t, struct tree_node *node, struct board *b, enum stone color, int radar, struct uct_policy *policy, int parity)
 331 {
 332         struct tree_node *ni = tree_init_node(t, pass, node->depth + 1);
 333         ni->parent = node; node->children = ni;
 334         if (policy->prior)
 335                 policy->prior(policy, t, ni, b, color, parity);
 336
 337         /* The loop considers only the symmetry playground. */
 338         if (UDEBUGL(6)) {
 339                 fprintf(stderr, "expanding %s within [%d,%d],[%d,%d] %d-%d\n",
 340                                 coord2sstr(node->coord, b),
 341                                 b->symmetry.x1, b->symmetry.y1,
 342                                 b->symmetry.x2, b->symmetry.y2,
 343                                 b->symmetry.type, b->symmetry.d);
 344         }
 345         for (int i = b->symmetry.x1; i <= b->symmetry.x2; i++) {
 346                 for (int j = b->symmetry.y1; j <= b->symmetry.y2; j++) {
 347                         if (b->symmetry.d) {
 348                                 int x = b->symmetry.type == SYM_DIAG_DOWN ? board_size(b) - 1 - i : i;
 349                                 if (x > j) {
 350                                         if (UDEBUGL(7))
 351                                                 fprintf(stderr, "drop %d,%d\n", i, j);
 352                                         continue;
 353                                 }
 354                         }
 355
 356                         coord_t c = coord_xy_otf(i, j, t->board);
 357                         if (board_at(b, c) != S_NONE)
 358                                 continue;
 359                         /* This looks very useful on large boards - weeds out huge amount of crufty moves. */
 360                         if (b->hash /* not empty board */ && radar && !board_stone_radar(b, c, radar))
 361                                 continue;
 362
 363                         struct tree_node *nj = tree_init_node(t, c, node->depth + 1);
 364                         nj->parent = node; ni->sibling = nj; ni = nj;
 365
 366                         if (policy->prior)
 367                                 policy->prior(policy, t, ni, b, color, parity);
 368                 }
 369         }
 370 }
 371
 372
 373 static coord_t
 374 flip_coord(struct board *b, coord_t c,
 375            bool flip_horiz, bool flip_vert, int flip_diag)
 376 {
 377         int x = coord_x(c, b), y = coord_y(c, b);
 378         if (flip_diag) {
 379                 int z = x; x = y; y = z;
 380         }
 381         if (flip_horiz) {
 382                 x = board_size(b) - 1 - x;
 383         }
 384         if (flip_vert) {
 385                 y = board_size(b) - 1 - y;
 386         }
 387         return coord_xy_otf(x, y, b);
 388 }
 389
 390 static void
 391 tree_fix_node_symmetry(struct board *b, struct tree_node *node,
 392                        bool flip_horiz, bool flip_vert, int flip_diag)
 393 {
 394         node->coord = flip_coord(b, node->coord, flip_horiz, flip_vert, flip_diag);
 395
 396         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 397                 tree_fix_node_symmetry(b, ni, flip_horiz, flip_vert, flip_diag);
 398 }
 399
 400 static void
 401 tree_fix_symmetry(struct tree *tree, struct board *b, coord_t c)
 402 {
 403         struct board_symmetry *s = &tree->root_symmetry;
 404         int cx = coord_x(c, b), cy = coord_y(c, b);
 405
 406         /* playground   X->h->v->d normalization
 407          * :::..        .d...
 408          * .::..        v....
 409          * ..:..        .....
 410          * .....        h...X
 411          * .....        .....  */
 412         bool flip_horiz = cx < s->x1 || cx > s->x2;
 413         bool flip_vert = cy < s->y1 || cy > s->y2;
 414
 415         bool flip_diag = 0;
 416         if (s->d) {
 417                 bool dir = (s->type == SYM_DIAG_DOWN);
 418                 int x = dir ^ flip_horiz ^ flip_vert ? board_size(b) - 1 - cx : cx;
 419                 if (flip_vert ? x < cy : x > cy) {
 420                         flip_diag = 1;
 421                 }
 422         }
 423
 424         if (UDEBUGL(4)) {
 425                 fprintf(stderr, "%s will flip %d %d %d -> %s, sym %d (%d) -> %d (%d)\n",
 426                         coord2sstr(c, b), flip_horiz, flip_vert, flip_diag,
 427                         coord2sstr(flip_coord(b, c, flip_horiz, flip_vert, flip_diag), b),
 428                         s->type, s->d, b->symmetry.type, b->symmetry.d);
 429         }
 430         tree_fix_node_symmetry(b, tree->root, flip_horiz, flip_vert, flip_diag);
 431 }
 432
 433
 434 static void
 435 tree_unlink_node(struct tree_node *node)
 436 {
 437         struct tree_node *ni = node->parent;
 438         if (ni->children == node) {
 439                 ni->children = node->sibling;
 440         } else {
 441                 ni = ni->children;
 442                 while (ni->sibling != node)
 443                         ni = ni->sibling;
 444                 ni->sibling = node->sibling;
 445         }
 446 }
 447
 448 void
 449 tree_delete_node(struct tree *tree, struct tree_node *node)
 450 {
 451         tree_unlink_node(node);
 452         tree_done_node(tree, node);
 453 }
 454
 455 void
 456 tree_promote_node(struct tree *tree, struct tree_node *node)
 457 {
 458         assert(node->parent == tree->root);
 459         tree_unlink_node(node);
 460         tree_done_node(tree, tree->root);
 461         tree->root = node;
 462         board_symmetry_update(tree->board, &tree->root_symmetry, node->coord);
 463         node->parent = NULL;
 464 }
 465
 466 bool
 467 tree_promote_at(struct tree *tree, struct board *b, coord_t c)
 468 {
 469         tree_fix_symmetry(tree, b, c);
 470
 471         for (struct tree_node *ni = tree->root->children; ni; ni = ni->sibling) {
 472                 if (ni->coord == c) {
 473                         tree_promote_node(tree, ni);
 474                         return true;
 475                 }
 476         }
 477         return false;
 478 }
 479
 480 bool
 481 tree_leaf_node(struct tree_node *node)
 482 {
 483         return !(node->children);
 484 }
 485
 486 void
 487 tree_update_node_value(struct tree_node *node)
 488 {
 489         bool noamaf = node->hints & NODE_HINT_NOAMAF;
 490         node->u.value = (float)(node->u.wins + node->prior.wins + (!noamaf ? node->amaf.wins : 0))
 491                         / (node->u.playouts + node->prior.playouts + (!noamaf ? node->amaf.playouts : 0));
 492 #if 0
 493         { struct board b2; board_size(&b2) = 9+2;
 494         fprintf(stderr, "%s->%s %d/%d %d/%d %f\n", node->parent ? coord2sstr(node->parent->coord, &b2) : NULL, coord2sstr(node->coord, &b2), node->u.wins, node->u.playouts, node->prior.wins, node->prior.playouts, node->u.value); }
 495 #endif
 496 }