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         sprintf(buf, "uctbook-%d-%02.01f.pachitree", b->size - 2, b->komi);
 106         return buf;
 107 }
 108
 109 static void
 110 tree_node_save(FILE *f, struct tree_node *node, int thres)
 111 {
 112         fputc(1, f);
 113         fwrite(((void *) node) + offsetof(struct tree_node, depth),
 114                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 115                1, f);
 116
 117         if (node->u.playouts >= thres)
 118                 for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 119                         tree_node_save(f, ni, thres);
 120
 121         fputc(0, f);
 122 }
 123
 124 void
 125 tree_save(struct tree *tree, struct board *b, int thres)
 126 {
 127         char *filename = tree_book_name(b);
 128         FILE *f = fopen(filename, "wb");
 129         if (!f) {
 130                 perror("fopen");
 131                 return;
 132         }
 133         tree_node_save(f, tree->root, thres);
 134         fputc(0, f);
 135         fclose(f);
 136 }
 137
 138
 139 void
 140 tree_node_load(FILE *f, struct tree_node *node, int *num, bool invert)
 141 {
 142         (*num)++;
 143
 144         fread(((void *) node) + offsetof(struct tree_node, depth),
 145                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 146                1, f);
 147
 148         /* Keep values in sane scale, otherwise we start overflowing.
 149          * We may go slow here but we must be careful about not getting
 150          * too huge integers.*/
 151 #define MAX_PLAYOUTS    10000000
 152         if (node->u.playouts > MAX_PLAYOUTS) {
 153                 int over = node->u.playouts - MAX_PLAYOUTS;
 154                 node->u.wins -= ((double) node->u.wins / node->u.playouts) * over;
 155                 node->u.playouts = MAX_PLAYOUTS;
 156         }
 157         if (node->amaf.playouts > MAX_PLAYOUTS) {
 158                 int over = node->amaf.playouts - MAX_PLAYOUTS;
 159                 node->amaf.wins -= ((double) node->amaf.wins / node->amaf.playouts) * over;
 160                 node->amaf.playouts = MAX_PLAYOUTS;
 161         }
 162
 163         if (invert) {
 164                 node->u.wins = node->u.playouts - node->u.wins;
 165                 node->u.value = 1 - node->u.value;
 166                 node->amaf.wins = node->amaf.playouts - node->amaf.wins;
 167                 node->amaf.value = 1 - node->amaf.value;
 168                 node->prior.wins = node->prior.playouts - node->prior.wins;
 169                 node->prior.value = 1 - node->prior.value;
 170         }
 171
 172         struct tree_node *ni = NULL, *ni_prev = NULL;
 173         while (fgetc(f)) {
 174                 ni_prev = ni; ni = calloc(1, sizeof(*ni));
 175                 if (!node->children)
 176                         node->children = ni;
 177                 else
 178                         ni_prev->sibling = ni;
 179                 ni->parent = node;
 180                 tree_node_load(f, ni, num, invert);
 181         }
 182 }
 183
 184 void
 185 tree_load(struct tree *tree, struct board *b, enum stone color)
 186 {
 187         char *filename = tree_book_name(b);
 188         FILE *f = fopen(filename, "rb");
 189         if (!f)
 190                 return;
 191
 192         fprintf(stderr, "Loading opening book %s...\n", filename);
 193
 194         int num = 0;
 195         if (fgetc(f))
 196                 tree_node_load(f, tree->root, &num, color != S_BLACK);
 197         fprintf(stderr, "Loaded %d nodes.\n", num);
 198
 199         fclose(f);
 200 }
 201
 202
 203 static struct tree_node *
 204 tree_node_copy(struct tree_node *node)
 205 {
 206         struct tree_node *n2 = malloc(sizeof(*n2));
 207         *n2 = *node;
 208         if (!node->children)
 209                 return n2;
 210         struct tree_node *ni = node->children;
 211         struct tree_node *ni2 = tree_node_copy(ni);
 212         n2->children = ni2; ni2->parent = n2;
 213         while ((ni = ni->sibling)) {
 214                 ni2->sibling = tree_node_copy(ni);
 215                 ni2 = ni2->sibling; ni2->parent = n2;
 216         }
 217         return n2;
 218 }
 219
 220 struct tree *
 221 tree_copy(struct tree *tree)
 222 {
 223         struct tree *t2 = malloc(sizeof(*t2));
 224         *t2 = *tree;
 225         t2->root = tree_node_copy(tree->root);
 226         return t2;
 227 }
 228
 229
 230 static void
 231 tree_node_merge(struct tree_node *dest, struct tree_node *src)
 232 {
 233         dest->hints |= src->hints;
 234
 235         /* Merge the children, both are coord-sorted lists. */
 236         struct tree_node *di = dest->children, *dip = NULL;
 237         struct tree_node *si = src->children, *sip = NULL;
 238         while (di && si) {
 239                 if (di->coord != si->coord) {
 240                         /* src has some extra items or misses di */
 241                         struct tree_node *si2 = si->sibling;
 242                         while (si2 && di->coord != si2->coord) {
 243                                 si2 = si2->sibling;
 244                         }
 245                         if (!si2)
 246                                 goto next_di; /* src misses di, move on */
 247                         /* chain the extra [si,si2) items before di */
 248                         if (dip)
 249                                 dip->sibling = si;
 250                         else
 251                                 dest->children = si;
 252                         while (si->sibling != si2) {
 253                                 si->parent = dest;
 254                                 si = si->sibling;
 255                         }
 256                         si->sibling = di;
 257                         si = si2;
 258                         if (sip)
 259                                 sip->sibling = si;
 260                         else
 261                                 src->children = si;
 262                 }
 263                 /* Matching nodes - recurse... */
 264                 tree_node_merge(di, si);
 265                 /* ...and move on. */
 266                 sip = si; si = si->sibling;
 267 next_di:
 268                 dip = di; di = di->sibling;
 269         }
 270         if (si) {
 271                 if (dip)
 272                         dip->sibling = si;
 273                 else
 274                         dest->children = si;
 275                 while (si) {
 276                         si->parent = dest;
 277                         si = si->sibling;
 278                 }
 279                 if (sip)
 280                         sip->sibling = NULL;
 281                 else
 282                         src->children = NULL;
 283         }
 284
 285         dest->prior.playouts += src->prior.playouts;
 286         dest->prior.wins += src->prior.wins;
 287         if (dest->prior.playouts)
 288                 dest->prior.value = dest->prior.wins / dest->prior.playouts;
 289         dest->amaf.playouts += src->amaf.playouts;
 290         dest->amaf.wins += src->amaf.wins;
 291         if (dest->amaf.playouts)
 292                 dest->amaf.value = dest->amaf.wins / dest->amaf.playouts;
 293         dest->u.playouts += src->u.playouts;
 294         dest->u.wins += src->u.wins;
 295         if (dest->prior.playouts + dest->amaf.playouts + dest->u.playouts)
 296                 tree_update_node_value(dest);
 297 }
 298
 299 /* Merge two trees built upon the same board. Note that the operation is
 300  * destructive on src. */
 301 void
 302 tree_merge(struct tree *dest, struct tree *src)
 303 {
 304         if (src->max_depth > dest->max_depth)
 305                 dest->max_depth = src->max_depth;
 306         tree_node_merge(dest->root, src->root);
 307 }
 308
 309
 310 /* Tree symmetry: When possible, we will localize the tree to a single part
 311  * of the board in tree_expand_node() and possibly flip along symmetry axes
 312  * to another part of the board in tree_promote_at(). We follow b->symmetry
 313  * guidelines here. */
 314
 315
 316 void
 317 tree_expand_node(struct tree *t, struct tree_node *node, struct board *b, enum stone color, int radar, struct uct_policy *policy, int parity)
 318 {
 319         struct tree_node *ni = tree_init_node(t, pass, node->depth + 1);
 320         ni->parent = node; node->children = ni;
 321
 322         /* The loop considers only the symmetry playground. */
 323         if (UDEBUGL(6)) {
 324                 fprintf(stderr, "expanding %s within [%d,%d],[%d,%d] %d-%d\n",
 325                                 coord2sstr(node->coord, b),
 326                                 b->symmetry.x1, b->symmetry.y1,
 327                                 b->symmetry.x2, b->symmetry.y2,
 328                                 b->symmetry.type, b->symmetry.d);
 329         }
 330         for (int i = b->symmetry.x1; i <= b->symmetry.x2; i++) {
 331                 for (int j = b->symmetry.y1; j <= b->symmetry.y2; j++) {
 332                         if (b->symmetry.d) {
 333                                 int x = b->symmetry.type == SYM_DIAG_DOWN ? board_size(b) - 1 - i : i;
 334                                 if (x > j) {
 335                                         if (UDEBUGL(7))
 336                                                 fprintf(stderr, "drop %d,%d\n", i, j);
 337                                         continue;
 338                                 }
 339                         }
 340
 341                         coord_t c = coord_xy_otf(i, j, t->board);
 342                         if (board_at(b, c) != S_NONE)
 343                                 continue;
 344                         /* This looks very useful on large boards - weeds out huge amount of crufty moves. */
 345                         if (b->hash /* not empty board */ && radar && !board_stone_radar(b, c, radar))
 346                                 continue;
 347
 348                         struct tree_node *nj = tree_init_node(t, c, node->depth + 1);
 349                         nj->parent = node; ni->sibling = nj; ni = nj;
 350
 351                         if (policy->prior)
 352                                 policy->prior(policy, t, ni, b, color, parity);
 353                 }
 354         }
 355 }
 356
 357
 358 static coord_t
 359 flip_coord(struct board *b, coord_t c,
 360            bool flip_horiz, bool flip_vert, int flip_diag)
 361 {
 362         int x = coord_x(c, b), y = coord_y(c, b);
 363         if (flip_diag) {
 364                 int z = x; x = y; y = z;
 365         }
 366         if (flip_horiz) {
 367                 x = board_size(b) - 1 - x;
 368         }
 369         if (flip_vert) {
 370                 y = board_size(b) - 1 - y;
 371         }
 372         return coord_xy_otf(x, y, b);
 373 }
 374
 375 static void
 376 tree_fix_node_symmetry(struct board *b, struct tree_node *node,
 377                        bool flip_horiz, bool flip_vert, int flip_diag)
 378 {
 379         node->coord = flip_coord(b, node->coord, flip_horiz, flip_vert, flip_diag);
 380
 381         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 382                 tree_fix_node_symmetry(b, ni, flip_horiz, flip_vert, flip_diag);
 383 }
 384
 385 static void
 386 tree_fix_symmetry(struct tree *tree, struct board *b, coord_t c)
 387 {
 388         struct board_symmetry *s = &tree->root_symmetry;
 389         int cx = coord_x(c, b), cy = coord_y(c, b);
 390
 391         /* playground   X->h->v->d normalization
 392          * :::..        .d...
 393          * .::..        v....
 394          * ..:..        .....
 395          * .....        h...X
 396          * .....        .....  */
 397         bool flip_horiz = cx < s->x1 || cx > s->x2;
 398         bool flip_vert = cy < s->y1 || cy > s->y2;
 399
 400         bool flip_diag = 0;
 401         if (s->d) {
 402                 bool dir = (s->type == SYM_DIAG_DOWN);
 403                 int x = dir ^ flip_horiz ^ flip_vert ? board_size(b) - 1 - cx : cx;
 404                 if (flip_vert ? x < cy : x > cy) {
 405                         flip_diag = 1;
 406                 }
 407         }
 408
 409         if (UDEBUGL(4)) {
 410                 fprintf(stderr, "%s will flip %d %d %d -> %s, sym %d (%d) -> %d (%d)\n",
 411                         coord2sstr(c, b), flip_horiz, flip_vert, flip_diag,
 412                         coord2sstr(flip_coord(b, c, flip_horiz, flip_vert, flip_diag), b),
 413                         s->type, s->d, b->symmetry.type, b->symmetry.d);
 414         }
 415         tree_fix_node_symmetry(b, tree->root, flip_horiz, flip_vert, flip_diag);
 416 }
 417
 418
 419 static void
 420 tree_unlink_node(struct tree_node *node)
 421 {
 422         struct tree_node *ni = node->parent;
 423         if (ni->children == node) {
 424                 ni->children = node->sibling;
 425         } else {
 426                 ni = ni->children;
 427                 while (ni->sibling != node)
 428                         ni = ni->sibling;
 429                 ni->sibling = node->sibling;
 430         }
 431 }
 432
 433 void
 434 tree_delete_node(struct tree *tree, struct tree_node *node)
 435 {
 436         tree_unlink_node(node);
 437         tree_done_node(tree, node);
 438 }
 439
 440 void
 441 tree_promote_node(struct tree *tree, struct tree_node *node)
 442 {
 443         assert(node->parent == tree->root);
 444         tree_unlink_node(node);
 445         tree_done_node(tree, tree->root);
 446         tree->root = node;
 447         board_symmetry_update(tree->board, &tree->root_symmetry, node->coord);
 448         node->parent = NULL;
 449 }
 450
 451 bool
 452 tree_promote_at(struct tree *tree, struct board *b, coord_t c)
 453 {
 454         tree_fix_symmetry(tree, b, c);
 455
 456         for (struct tree_node *ni = tree->root->children; ni; ni = ni->sibling) {
 457                 if (ni->coord == c) {
 458                         tree_promote_node(tree, ni);
 459                         return true;
 460                 }
 461         }
 462         return false;
 463 }
 464
 465 bool
 466 tree_leaf_node(struct tree_node *node)
 467 {
 468         return !(node->children);
 469 }
 470
 471 void
 472 tree_update_node_value(struct tree_node *node)
 473 {
 474         bool noamaf = node->hints & NODE_HINT_NOAMAF;
 475         node->u.value = (float)(node->u.wins + node->prior.wins + (!noamaf ? node->amaf.wins : 0))
 476                         / (node->u.playouts + node->prior.playouts + (!noamaf ? node->amaf.playouts : 0));
 477 #if 0
 478         { struct board b2; board_size(&b2) = 9+2;
 479         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); }
 480 #endif
 481 }