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         static long c = 1000000;
  25         n->hash = c++;
  26         if (depth > t->max_depth)
  27                 t->max_depth = depth;
  28         return n;
  29 }
  30
  31 struct tree *
  32 tree_init(struct board *board, enum stone color)
  33 {
  34         struct tree *t = calloc(1, sizeof(*t));
  35         t->board = board;
  36         /* The root PASS move is only virtual, we never play it. */
  37         t->root = tree_init_node(t, pass, 0);
  38         t->root_symmetry = board->symmetry;
  39         t->root_color = stone_other(color); // to research black moves, root will be white
  40         return t;
  41 }
  42
  43
  44 static void
  45 tree_done_node(struct tree *t, struct tree_node *n)
  46 {
  47         struct tree_node *ni = n->children;
  48         while (ni) {
  49                 struct tree_node *nj = ni->sibling;
  50                 tree_done_node(t, ni);
  51                 ni = nj;
  52         }
  53         free(n);
  54 }
  55
  56 void
  57 tree_done(struct tree *t)
  58 {
  59         tree_done_node(t, t->root);
  60         free(t);
  61 }
  62
  63
  64 static void
  65 tree_node_dump(struct tree *tree, struct tree_node *node, int l, int thres)
  66 {
  67         for (int i = 0; i < l; i++) fputc(' ', stderr);
  68         int children = 0;
  69         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
  70                 children++;
  71         /* We use 1 as parity, since for all nodes we want to know the
  72          * win probability of _us_, not the node color. */
  73         fprintf(stderr, "[%s] %f (%d/%d playouts [prior %d/%d amaf %d/%d]; hints %x; %d children) <%lld>\n",
  74                 coord2sstr(node->coord, tree->board),
  75                 tree_node_get_value(tree, node, u, 1),
  76                 tree_node_get_wins(tree, node, u, 1), node->u.playouts,
  77                 tree_node_get_wins(tree, node, prior, 1), node->prior.playouts,
  78                 tree_node_get_wins(tree, node, amaf, 1), node->amaf.playouts,
  79                 node->hints, children, node->hash);
  80
  81         /* Print nodes sorted by #playouts. */
  82
  83         struct tree_node *nbox[1000]; int nboxl = 0;
  84         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
  85                 if (ni->u.playouts > thres)
  86                         nbox[nboxl++] = ni;
  87
  88         while (true) {
  89                 int best = -1;
  90                 for (int i = 0; i < nboxl; i++)
  91                         if (nbox[i] && (best < 0 || nbox[i]->u.playouts > nbox[best]->u.playouts))
  92                                 best = i;
  93                 if (best < 0)
  94                         break;
  95                 tree_node_dump(tree, nbox[best], l + 1, /* node->u.value < 0.1 ? 0 : */ thres);
  96                 nbox[best] = NULL;
  97         }
  98 }
  99
 100 void
 101 tree_dump(struct tree *tree, int thres)
 102 {
 103         if (thres && tree->root->u.playouts / thres > 100) {
 104                 /* Be a bit sensible about this; the opening book can create
 105                  * huge dumps at first. */
 106                 thres = tree->root->u.playouts / 100 * (thres < 1000 ? 1 : thres / 1000);
 107         }
 108         tree_node_dump(tree, tree->root, 0, thres);
 109 }
 110
 111
 112 static char *
 113 tree_book_name(struct board *b)
 114 {
 115         static char buf[256];
 116         if (b->handicap > 0) {
 117                 sprintf(buf, "uctbook-%d-%02.01f-h%d.pachitree", b->size - 2, b->komi, b->handicap);
 118         } else {
 119                 sprintf(buf, "uctbook-%d-%02.01f.pachitree", b->size - 2, b->komi);
 120         }
 121         return buf;
 122 }
 123
 124 static void
 125 tree_node_save(FILE *f, struct tree_node *node, int thres)
 126 {
 127         fputc(1, f);
 128         fwrite(((void *) node) + offsetof(struct tree_node, depth),
 129                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 130                1, f);
 131
 132         if (node->u.playouts >= thres)
 133                 for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 134                         tree_node_save(f, ni, thres);
 135
 136         fputc(0, f);
 137 }
 138
 139 void
 140 tree_save(struct tree *tree, struct board *b, int thres)
 141 {
 142         char *filename = tree_book_name(b);
 143         FILE *f = fopen(filename, "wb");
 144         if (!f) {
 145                 perror("fopen");
 146                 return;
 147         }
 148         tree_node_save(f, tree->root, thres);
 149         fputc(0, f);
 150         fclose(f);
 151 }
 152
 153
 154 void
 155 tree_node_load(FILE *f, struct tree_node *node, int *num)
 156 {
 157         (*num)++;
 158
 159         fread(((void *) node) + offsetof(struct tree_node, depth),
 160                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 161                1, f);
 162
 163         /* Keep values in sane scale, otherwise we start overflowing.
 164          * We may go slow here but we must be careful about not getting
 165          * too huge integers.*/
 166 #define MAX_PLAYOUTS    10000000
 167         if (node->u.playouts > MAX_PLAYOUTS) {
 168                 int over = node->u.playouts - MAX_PLAYOUTS;
 169                 node->u.wins -= ((double) node->u.wins / node->u.playouts) * over;
 170                 node->u.playouts = MAX_PLAYOUTS;
 171         }
 172         if (node->amaf.playouts > MAX_PLAYOUTS) {
 173                 int over = node->amaf.playouts - MAX_PLAYOUTS;
 174                 node->amaf.wins -= ((double) node->amaf.wins / node->amaf.playouts) * over;
 175                 node->amaf.playouts = MAX_PLAYOUTS;
 176         }
 177
 178         struct tree_node *ni = NULL, *ni_prev = NULL;
 179         while (fgetc(f)) {
 180                 ni_prev = ni; ni = calloc(1, sizeof(*ni));
 181                 if (!node->children)
 182                         node->children = ni;
 183                 else
 184                         ni_prev->sibling = ni;
 185                 ni->parent = node;
 186                 tree_node_load(f, ni, num);
 187         }
 188 }
 189
 190 void
 191 tree_load(struct tree *tree, struct board *b)
 192 {
 193         char *filename = tree_book_name(b);
 194         FILE *f = fopen(filename, "rb");
 195         if (!f)
 196                 return;
 197
 198         fprintf(stderr, "Loading opening book %s...\n", filename);
 199
 200         int num = 0;
 201         if (fgetc(f))
 202                 tree_node_load(f, tree->root, &num);
 203         fprintf(stderr, "Loaded %d nodes.\n", num);
 204
 205         fclose(f);
 206 }
 207
 208
 209 static struct tree_node *
 210 tree_node_copy(struct tree_node *node)
 211 {
 212         struct tree_node *n2 = malloc(sizeof(*n2));
 213         *n2 = *node;
 214         if (!node->children)
 215                 return n2;
 216         struct tree_node *ni = node->children;
 217         struct tree_node *ni2 = tree_node_copy(ni);
 218         n2->children = ni2; ni2->parent = n2;
 219         while ((ni = ni->sibling)) {
 220                 ni2->sibling = tree_node_copy(ni);
 221                 ni2 = ni2->sibling; ni2->parent = n2;
 222         }
 223         return n2;
 224 }
 225
 226 struct tree *
 227 tree_copy(struct tree *tree)
 228 {
 229         struct tree *t2 = malloc(sizeof(*t2));
 230         *t2 = *tree;
 231         t2->root = tree_node_copy(tree->root);
 232         return t2;
 233 }
 234
 235
 236 static void
 237 tree_node_merge(struct tree_node *dest, struct tree_node *src)
 238 {
 239         dest->hints |= src->hints;
 240
 241         /* Merge the children, both are coord-sorted lists. */
 242         struct tree_node *di = dest->children, **dref = &dest->children;
 243         struct tree_node *si = src->children, **sref = &src->children;
 244         while (di && si) {
 245                 if (di->coord != si->coord) {
 246                         /* src has some extra items or misses di */
 247                         struct tree_node *si2 = si->sibling;
 248                         while (si2 && di->coord != si2->coord) {
 249                                 si2 = si2->sibling;
 250                         }
 251                         if (!si2)
 252                                 goto next_di; /* src misses di, move on */
 253                         /* chain the extra [si,si2) items before di */
 254                         (*dref) = si;
 255                         while (si->sibling != si2) {
 256                                 si->parent = dest;
 257                                 si = si->sibling;
 258                         }
 259                         si->parent = dest;
 260                         si->sibling = di;
 261                         si = si2;
 262                         (*sref) = si;
 263                 }
 264                 /* Matching nodes - recurse... */
 265                 tree_node_merge(di, si);
 266                 /* ...and move on. */
 267                 sref = &si->sibling; si = si->sibling;
 268 next_di:
 269                 dref = &di->sibling; di = di->sibling;
 270         }
 271         if (si) {
 272                 /* Some outstanding nodes are left on src side, rechain
 273                  * them to dst. */
 274                 (*dref) = si;
 275                 while (si) {
 276                         si->parent = dest;
 277                         si = si->sibling;
 278                 }
 279                 (*sref) = NULL;
 280         }
 281
 282         /* Priors should be constant. */
 283         assert(dest->prior.playouts == src->prior.playouts && dest->prior.wins == src->prior.wins);
 284
 285         dest->amaf.playouts += src->amaf.playouts;
 286         dest->amaf.wins += src->amaf.wins;
 287         if (dest->amaf.playouts)
 288                 dest->amaf.value = (float) dest->amaf.wins / dest->amaf.playouts;
 289
 290         dest->u.playouts += src->u.playouts;
 291         dest->u.wins += src->u.wins;
 292         if (dest->prior.playouts + dest->amaf.playouts + dest->u.playouts)
 293                 tree_update_node_value(dest);
 294 }
 295
 296 /* Merge two trees built upon the same board. Note that the operation is
 297  * destructive on src. */
 298 void
 299 tree_merge(struct tree *dest, struct tree *src)
 300 {
 301         if (src->max_depth > dest->max_depth)
 302                 dest->max_depth = src->max_depth;
 303         tree_node_merge(dest->root, src->root);
 304 }
 305
 306
 307 static void
 308 tree_node_normalize(struct tree_node *node, int factor)
 309 {
 310         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 311                 tree_node_normalize(ni, factor);
 312
 313 #define normalize(s1, s2, t) node->s2.t = node->s1.t + (node->s2.t - node->s1.t) / factor;
 314         normalize(pamaf, amaf, playouts);
 315         normalize(pamaf, amaf, wins);
 316         memcpy(&node->pamaf, &node->amaf, sizeof(node->amaf));
 317
 318         normalize(pu, u, playouts);
 319         normalize(pu, u, wins);
 320         memcpy(&node->pu, &node->u, sizeof(node->u));
 321 #undef normalize
 322 }
 323
 324 /* Normalize a tree, dividing the amaf and u values by given
 325  * factor; otherwise, simulations run in independent threads
 326  * two trees built upon the same board. To correctly handle
 327  * results taken from previous simulation run, they are backed
 328  * up in tree. */
 329 void
 330 tree_normalize(struct tree *tree, int factor)
 331 {
 332         tree_node_normalize(tree->root, factor);
 333 }
 334
 335
 336 /* Tree symmetry: When possible, we will localize the tree to a single part
 337  * of the board in tree_expand_node() and possibly flip along symmetry axes
 338  * to another part of the board in tree_promote_at(). We follow b->symmetry
 339  * guidelines here. */
 340
 341
 342 void
 343 tree_expand_node(struct tree *t, struct tree_node *node, struct board *b, enum stone color, int radar, struct uct_policy *policy, int parity)
 344 {
 345         struct tree_node *ni = tree_init_node(t, pass, node->depth + 1);
 346         ni->parent = node; node->children = ni;
 347         if (policy->prior)
 348                 policy->prior(policy, t, ni, b, color, parity);
 349
 350         /* The loop considers only the symmetry playground. */
 351         if (UDEBUGL(6)) {
 352                 fprintf(stderr, "expanding %s within [%d,%d],[%d,%d] %d-%d\n",
 353                                 coord2sstr(node->coord, b),
 354                                 b->symmetry.x1, b->symmetry.y1,
 355                                 b->symmetry.x2, b->symmetry.y2,
 356                                 b->symmetry.type, b->symmetry.d);
 357         }
 358         for (int i = b->symmetry.x1; i <= b->symmetry.x2; i++) {
 359                 for (int j = b->symmetry.y1; j <= b->symmetry.y2; j++) {
 360                         if (b->symmetry.d) {
 361                                 int x = b->symmetry.type == SYM_DIAG_DOWN ? board_size(b) - 1 - i : i;
 362                                 if (x > j) {
 363                                         if (UDEBUGL(7))
 364                                                 fprintf(stderr, "drop %d,%d\n", i, j);
 365                                         continue;
 366                                 }
 367                         }
 368
 369                         coord_t c = coord_xy_otf(i, j, t->board);
 370                         if (board_at(b, c) != S_NONE)
 371                                 continue;
 372                         assert(c != node->coord); // I have spotted "C3 C3" in some sequence...
 373                         /* This looks very useful on large boards - weeds out huge amount of crufty moves. */
 374                         if (b->hash /* not empty board */ && radar && !board_stone_radar(b, c, radar))
 375                                 continue;
 376
 377                         struct tree_node *nj = tree_init_node(t, c, node->depth + 1);
 378                         nj->parent = node; ni->sibling = nj; ni = nj;
 379
 380                         if (policy->prior)
 381                                 policy->prior(policy, t, ni, b, color, parity);
 382                 }
 383         }
 384 }
 385
 386
 387 static coord_t
 388 flip_coord(struct board *b, coord_t c,
 389            bool flip_horiz, bool flip_vert, int flip_diag)
 390 {
 391         int x = coord_x(c, b), y = coord_y(c, b);
 392         if (flip_diag) {
 393                 int z = x; x = y; y = z;
 394         }
 395         if (flip_horiz) {
 396                 x = board_size(b) - 1 - x;
 397         }
 398         if (flip_vert) {
 399                 y = board_size(b) - 1 - y;
 400         }
 401         return coord_xy_otf(x, y, b);
 402 }
 403
 404 static void
 405 tree_fix_node_symmetry(struct board *b, struct tree_node *node,
 406                        bool flip_horiz, bool flip_vert, int flip_diag)
 407 {
 408         if (!is_pass(node->coord))
 409                 node->coord = flip_coord(b, node->coord, flip_horiz, flip_vert, flip_diag);
 410
 411         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 412                 tree_fix_node_symmetry(b, ni, flip_horiz, flip_vert, flip_diag);
 413 }
 414
 415 static void
 416 tree_fix_symmetry(struct tree *tree, struct board *b, coord_t c)
 417 {
 418         if (is_pass(c))
 419                 return;
 420
 421         struct board_symmetry *s = &tree->root_symmetry;
 422         int cx = coord_x(c, b), cy = coord_y(c, b);
 423
 424         /* playground   X->h->v->d normalization
 425          * :::..        .d...
 426          * .::..        v....
 427          * ..:..        .....
 428          * .....        h...X
 429          * .....        .....  */
 430         bool flip_horiz = cx < s->x1 || cx > s->x2;
 431         bool flip_vert = cy < s->y1 || cy > s->y2;
 432
 433         bool flip_diag = 0;
 434         if (s->d) {
 435                 bool dir = (s->type == SYM_DIAG_DOWN);
 436                 int x = dir ^ flip_horiz ^ flip_vert ? board_size(b) - 1 - cx : cx;
 437                 if (flip_vert ? x < cy : x > cy) {
 438                         flip_diag = 1;
 439                 }
 440         }
 441
 442         if (UDEBUGL(4)) {
 443                 fprintf(stderr, "%s will flip %d %d %d -> %s, sym %d (%d) -> %d (%d)\n",
 444                         coord2sstr(c, b), flip_horiz, flip_vert, flip_diag,
 445                         coord2sstr(flip_coord(b, c, flip_horiz, flip_vert, flip_diag), b),
 446                         s->type, s->d, b->symmetry.type, b->symmetry.d);
 447         }
 448         if (flip_horiz || flip_vert || flip_diag)
 449                 tree_fix_node_symmetry(b, tree->root, flip_horiz, flip_vert, flip_diag);
 450 }
 451
 452
 453 static void
 454 tree_unlink_node(struct tree_node *node)
 455 {
 456         struct tree_node *ni = node->parent;
 457         if (ni->children == node) {
 458                 ni->children = node->sibling;
 459         } else {
 460                 ni = ni->children;
 461                 while (ni->sibling != node)
 462                         ni = ni->sibling;
 463                 ni->sibling = node->sibling;
 464         }
 465         node->sibling = NULL;
 466         node->parent = NULL;
 467 }
 468
 469 void
 470 tree_delete_node(struct tree *tree, struct tree_node *node)
 471 {
 472         tree_unlink_node(node);
 473         tree_done_node(tree, node);
 474 }
 475
 476 void
 477 tree_promote_node(struct tree *tree, struct tree_node *node)
 478 {
 479         assert(node->parent == tree->root);
 480         tree_unlink_node(node);
 481         tree_done_node(tree, tree->root);
 482         tree->root = node;
 483         tree->root_color = stone_other(tree->root_color);
 484         board_symmetry_update(tree->board, &tree->root_symmetry, node->coord);
 485 }
 486
 487 bool
 488 tree_promote_at(struct tree *tree, struct board *b, coord_t c)
 489 {
 490         tree_fix_symmetry(tree, b, c);
 491
 492         for (struct tree_node *ni = tree->root->children; ni; ni = ni->sibling) {
 493                 if (ni->coord == c) {
 494                         tree_promote_node(tree, ni);
 495                         return true;
 496                 }
 497         }
 498         return false;
 499 }
 500
 501 bool
 502 tree_leaf_node(struct tree_node *node)
 503 {
 504         return !(node->children);
 505 }
 506
 507 void
 508 tree_update_node_value(struct tree_node *node)
 509 {
 510         bool noamaf = node->hints & NODE_HINT_NOAMAF;
 511         node->u.value = (float)(node->u.wins + node->prior.wins + (!noamaf ? node->amaf.wins : 0))
 512                         / (node->u.playouts + node->prior.playouts + (!noamaf ? node->amaf.playouts : 0));
 513 #if 0
 514         { struct board b2; board_size(&b2) = 9+2;
 515         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); }
 516 #endif
 517 }