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 "tactics.h"
  15 #include "uct/internal.h"
  16 #include "uct/prior.h"
  17 #include "uct/tree.h"
  18
  19
  20 static struct tree_node *
  21 tree_init_node(struct tree *t, coord_t coord, int depth)
  22 {
  23         struct tree_node *n = calloc(1, sizeof(*n));
  24         if (!n) {
  25                 fprintf(stderr, "tree_init_node(): OUT OF MEMORY\n");
  26                 exit(1);
  27         }
  28         n->coord = coord;
  29         n->depth = depth;
  30         static long c = 1000000;
  31         n->hash = c++;
  32         if (depth > t->max_depth)
  33                 t->max_depth = depth;
  34         return n;
  35 }
  36
  37 struct tree *
  38 tree_init(struct board *board, enum stone color)
  39 {
  40         struct tree *t = calloc(1, sizeof(*t));
  41         t->board = board;
  42         /* The root PASS move is only virtual, we never play it. */
  43         t->root = tree_init_node(t, pass, 0);
  44         t->root_symmetry = board->symmetry;
  45         t->root_color = stone_other(color); // to research black moves, root will be white
  46         return t;
  47 }
  48
  49
  50 static void
  51 tree_done_node(struct tree *t, struct tree_node *n)
  52 {
  53         struct tree_node *ni = n->children;
  54         while (ni) {
  55                 struct tree_node *nj = ni->sibling;
  56                 tree_done_node(t, ni);
  57                 ni = nj;
  58         }
  59         free(n);
  60 }
  61
  62 void
  63 tree_done(struct tree *t)
  64 {
  65         tree_done_node(t, t->root);
  66         free(t);
  67 }
  68
  69
  70 static void
  71 tree_node_dump(struct tree *tree, struct tree_node *node, int l, int thres)
  72 {
  73         for (int i = 0; i < l; i++) fputc(' ', stderr);
  74         int children = 0;
  75         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
  76                 children++;
  77         /* We use 1 as parity, since for all nodes we want to know the
  78          * win probability of _us_, not the node color. */
  79         fprintf(stderr, "[%s] %f %% %d [prior %f %% %d amaf %f %% %d]; hints %x; %d children <%lld>\n",
  80                 coord2sstr(node->coord, tree->board),
  81                 tree_node_get_value(tree, node, u, 1), node->u.playouts,
  82                 tree_node_get_value(tree, node, prior, 1), node->prior.playouts,
  83                 tree_node_get_value(tree, node, amaf, 1), node->amaf.playouts,
  84                 node->hints, children, node->hash);
  85
  86         /* Print nodes sorted by #playouts. */
  87
  88         struct tree_node *nbox[1000]; int nboxl = 0;
  89         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
  90                 if (ni->u.playouts > thres)
  91                         nbox[nboxl++] = ni;
  92
  93         while (true) {
  94                 int best = -1;
  95                 for (int i = 0; i < nboxl; i++)
  96                         if (nbox[i] && (best < 0 || nbox[i]->u.playouts > nbox[best]->u.playouts))
  97                                 best = i;
  98                 if (best < 0)
  99                         break;
 100                 tree_node_dump(tree, nbox[best], l + 1, /* node->u.value < 0.1 ? 0 : */ thres);
 101                 nbox[best] = NULL;
 102         }
 103 }
 104
 105 void
 106 tree_dump(struct tree *tree, int thres)
 107 {
 108         if (thres && tree->root->u.playouts / thres > 100) {
 109                 /* Be a bit sensible about this; the opening book can create
 110                  * huge dumps at first. */
 111                 thres = tree->root->u.playouts / 100 * (thres < 1000 ? 1 : thres / 1000);
 112         }
 113         fprintf(stderr, "(UCT tree; root %s; extra komi %f)\n",
 114                 stone2str(tree->root_color), tree->extra_komi);
 115         tree_node_dump(tree, tree->root, 0, thres);
 116 }
 117
 118
 119 static char *
 120 tree_book_name(struct board *b)
 121 {
 122         static char buf[256];
 123         if (b->handicap > 0) {
 124                 sprintf(buf, "uctbook-%d-%02.01f-h%d.pachitree", b->size - 2, b->komi, b->handicap);
 125         } else {
 126                 sprintf(buf, "uctbook-%d-%02.01f.pachitree", b->size - 2, b->komi);
 127         }
 128         return buf;
 129 }
 130
 131 static void
 132 tree_node_save(FILE *f, struct tree_node *node, int thres)
 133 {
 134         fputc(1, f);
 135         fwrite(((void *) node) + offsetof(struct tree_node, depth),
 136                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 137                1, f);
 138
 139         if (node->u.playouts >= thres)
 140                 for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 141                         tree_node_save(f, ni, thres);
 142
 143         fputc(0, f);
 144 }
 145
 146 void
 147 tree_save(struct tree *tree, struct board *b, int thres)
 148 {
 149         char *filename = tree_book_name(b);
 150         FILE *f = fopen(filename, "wb");
 151         if (!f) {
 152                 perror("fopen");
 153                 return;
 154         }
 155         tree_node_save(f, tree->root, thres);
 156         fputc(0, f);
 157         fclose(f);
 158 }
 159
 160
 161 void
 162 tree_node_load(FILE *f, struct tree_node *node, int *num)
 163 {
 164         (*num)++;
 165
 166         fread(((void *) node) + offsetof(struct tree_node, depth),
 167                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 168                1, f);
 169
 170         /* Keep values in sane scale, otherwise we start overflowing. */
 171 #define MAX_PLAYOUTS    10000000
 172         if (node->u.playouts > MAX_PLAYOUTS) {
 173                 node->u.playouts = MAX_PLAYOUTS;
 174         }
 175         if (node->amaf.playouts > MAX_PLAYOUTS) {
 176                 node->amaf.playouts = MAX_PLAYOUTS;
 177         }
 178
 179         memcpy(&node->pamaf, &node->amaf, sizeof(node->amaf));
 180         memcpy(&node->pu, &node->u, sizeof(node->u));
 181
 182         struct tree_node *ni = NULL, *ni_prev = NULL;
 183         while (fgetc(f)) {
 184                 ni_prev = ni; ni = calloc(1, sizeof(*ni));
 185                 if (!node->children)
 186                         node->children = ni;
 187                 else
 188                         ni_prev->sibling = ni;
 189                 ni->parent = node;
 190                 tree_node_load(f, ni, num);
 191         }
 192 }
 193
 194 void
 195 tree_load(struct tree *tree, struct board *b)
 196 {
 197         char *filename = tree_book_name(b);
 198         FILE *f = fopen(filename, "rb");
 199         if (!f)
 200                 return;
 201
 202         fprintf(stderr, "Loading opening book %s...\n", filename);
 203
 204         int num = 0;
 205         if (fgetc(f))
 206                 tree_node_load(f, tree->root, &num);
 207         fprintf(stderr, "Loaded %d nodes.\n", num);
 208
 209         fclose(f);
 210 }
 211
 212
 213 static struct tree_node *
 214 tree_node_copy(struct tree_node *node)
 215 {
 216         struct tree_node *n2 = malloc(sizeof(*n2));
 217         *n2 = *node;
 218         if (!node->children)
 219                 return n2;
 220         struct tree_node *ni = node->children;
 221         struct tree_node *ni2 = tree_node_copy(ni);
 222         n2->children = ni2; ni2->parent = n2;
 223         while ((ni = ni->sibling)) {
 224                 ni2->sibling = tree_node_copy(ni);
 225                 ni2 = ni2->sibling; ni2->parent = n2;
 226         }
 227         return n2;
 228 }
 229
 230 struct tree *
 231 tree_copy(struct tree *tree)
 232 {
 233         struct tree *t2 = malloc(sizeof(*t2));
 234         *t2 = *tree;
 235         t2->root = tree_node_copy(tree->root);
 236         return t2;
 237 }
 238
 239
 240 static void
 241 tree_node_merge(struct tree_node *dest, struct tree_node *src)
 242 {
 243         /* Do not merge nodes that weren't touched at all. */
 244         assert(dest->pamaf.playouts == src->pamaf.playouts);
 245         assert(dest->pu.playouts == src->pu.playouts);
 246         if (src->amaf.playouts - src->pamaf.playouts == 0
 247             && src->u.playouts - src->pu.playouts == 0) {
 248                 return;
 249         }
 250
 251         dest->hints |= src->hints;
 252
 253         /* Merge the children, both are coord-sorted lists. */
 254         struct tree_node *di = dest->children, **dref = &dest->children;
 255         struct tree_node *si = src->children, **sref = &src->children;
 256         while (di && si) {
 257                 if (di->coord != si->coord) {
 258                         /* src has some extra items or misses di */
 259                         struct tree_node *si2 = si->sibling;
 260                         while (si2 && di->coord != si2->coord) {
 261                                 si2 = si2->sibling;
 262                         }
 263                         if (!si2)
 264                                 goto next_di; /* src misses di, move on */
 265                         /* chain the extra [si,si2) items before di */
 266                         (*dref) = si;
 267                         while (si->sibling != si2) {
 268                                 si->parent = dest;
 269                                 si = si->sibling;
 270                         }
 271                         si->parent = dest;
 272                         si->sibling = di;
 273                         si = si2;
 274                         (*sref) = si;
 275                 }
 276                 /* Matching nodes - recurse... */
 277                 tree_node_merge(di, si);
 278                 /* ...and move on. */
 279                 sref = &si->sibling; si = si->sibling;
 280 next_di:
 281                 dref = &di->sibling; di = di->sibling;
 282         }
 283         if (si) {
 284                 /* Some outstanding nodes are left on src side, rechain
 285                  * them to dst. */
 286                 (*dref) = si;
 287                 while (si) {
 288                         si->parent = dest;
 289                         si = si->sibling;
 290                 }
 291                 (*sref) = NULL;
 292         }
 293
 294         /* Priors should be constant. */
 295         assert(dest->prior.playouts == src->prior.playouts && dest->prior.value == src->prior.value);
 296
 297         stats_merge(&dest->amaf, &src->amaf);
 298         stats_merge(&dest->u, &src->u);
 299 }
 300
 301 /* Merge two trees built upon the same board. Note that the operation is
 302  * destructive on src. */
 303 void
 304 tree_merge(struct tree *dest, struct tree *src)
 305 {
 306         if (src->max_depth > dest->max_depth)
 307                 dest->max_depth = src->max_depth;
 308         tree_node_merge(dest->root, src->root);
 309 }
 310
 311
 312 static void
 313 tree_node_normalize(struct tree_node *node, int factor)
 314 {
 315         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 316                 tree_node_normalize(ni, factor);
 317
 318 #define normalize(s1, s2, t) node->s2.t = node->s1.t + (node->s2.t - node->s1.t) / factor;
 319         normalize(pamaf, amaf, playouts);
 320         memcpy(&node->pamaf, &node->amaf, sizeof(node->amaf));
 321
 322         normalize(pu, u, playouts);
 323         memcpy(&node->pu, &node->u, sizeof(node->u));
 324 #undef normalize
 325 }
 326
 327 /* Normalize a tree, dividing the amaf and u values by given
 328  * factor; otherwise, simulations run in independent threads
 329  * two trees built upon the same board. To correctly handle
 330  * results taken from previous simulation run, they are backed
 331  * up in tree. */
 332 void
 333 tree_normalize(struct tree *tree, int factor)
 334 {
 335         tree_node_normalize(tree->root, factor);
 336 }
 337
 338
 339 /* Tree symmetry: When possible, we will localize the tree to a single part
 340  * of the board in tree_expand_node() and possibly flip along symmetry axes
 341  * to another part of the board in tree_promote_at(). We follow b->symmetry
 342  * guidelines here. */
 343
 344
 345 void
 346 tree_expand_node(struct tree *t, struct tree_node *node, struct board *b, enum stone color, int radar, struct uct *u, int parity)
 347 {
 348         /* First, get a map of prior values to initialize the new
 349          * nodes with. */
 350         struct prior_map map = {
 351                 .b = b,
 352                 .to_play = color,
 353                 .parity = tree_parity(t, parity),
 354         };
 355         // Include pass in the prior map.
 356         struct move_stats map_prior[board_size2(b) + 1]; map.prior = &map_prior[1];
 357         bool map_consider[board_size2(b) + 1]; map.consider = &map_consider[1];
 358         memset(map_prior, 0, sizeof(map_prior));
 359         memset(map_consider, 0, sizeof(map_consider));
 360         struct move pm = { .color = color };
 361         map.consider[pass] = true;
 362         foreach_point(b) {
 363                 if (board_at(b, c) != S_NONE)
 364                         continue;
 365                 /* This looks very useful on large boards - weeds out huge amount of crufty moves. */
 366                 if (b->hash /* not empty board */ && radar && !board_stone_radar(b, c, radar))
 367                         continue;
 368                 pm.coord = c;
 369                 if (!board_is_valid_move(b, &pm))
 370                         continue;
 371                 map.consider[c] = true;
 372         } foreach_point_end;
 373         uct_prior(u, node, &map);
 374
 375         /* Now, create the nodes. */
 376         struct tree_node *ni = tree_init_node(t, pass, node->depth + 1);
 377         ni->parent = node; node->children = ni;
 378         ni->prior = map.prior[pass];
 379
 380         /* The loop considers only the symmetry playground. */
 381         if (UDEBUGL(6)) {
 382                 fprintf(stderr, "expanding %s within [%d,%d],[%d,%d] %d-%d\n",
 383                                 coord2sstr(node->coord, b),
 384                                 b->symmetry.x1, b->symmetry.y1,
 385                                 b->symmetry.x2, b->symmetry.y2,
 386                                 b->symmetry.type, b->symmetry.d);
 387         }
 388         for (int i = b->symmetry.x1; i <= b->symmetry.x2; i++) {
 389                 for (int j = b->symmetry.y1; j <= b->symmetry.y2; j++) {
 390                         if (b->symmetry.d) {
 391                                 int x = b->symmetry.type == SYM_DIAG_DOWN ? board_size(b) - 1 - i : i;
 392                                 if (x > j) {
 393                                         if (UDEBUGL(7))
 394                                                 fprintf(stderr, "drop %d,%d\n", i, j);
 395                                         continue;
 396                                 }
 397                         }
 398
 399                         coord_t c = coord_xy_otf(i, j, t->board);
 400                         if (!map.consider[c]) // Filter out invalid moves
 401                                 continue;
 402                         assert(c != node->coord); // I have spotted "C3 C3" in some sequence...
 403
 404                         struct tree_node *nj = tree_init_node(t, c, node->depth + 1);
 405                         nj->parent = node; ni->sibling = nj; ni = nj;
 406
 407                         ni->prior = map.prior[c];
 408                 }
 409         }
 410 }
 411
 412
 413 static coord_t
 414 flip_coord(struct board *b, coord_t c,
 415            bool flip_horiz, bool flip_vert, int flip_diag)
 416 {
 417         int x = coord_x(c, b), y = coord_y(c, b);
 418         if (flip_diag) {
 419                 int z = x; x = y; y = z;
 420         }
 421         if (flip_horiz) {
 422                 x = board_size(b) - 1 - x;
 423         }
 424         if (flip_vert) {
 425                 y = board_size(b) - 1 - y;
 426         }
 427         return coord_xy_otf(x, y, b);
 428 }
 429
 430 static void
 431 tree_fix_node_symmetry(struct board *b, struct tree_node *node,
 432                        bool flip_horiz, bool flip_vert, int flip_diag)
 433 {
 434         if (!is_pass(node->coord))
 435                 node->coord = flip_coord(b, node->coord, flip_horiz, flip_vert, flip_diag);
 436
 437         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 438                 tree_fix_node_symmetry(b, ni, flip_horiz, flip_vert, flip_diag);
 439 }
 440
 441 static void
 442 tree_fix_symmetry(struct tree *tree, struct board *b, coord_t c)
 443 {
 444         if (is_pass(c))
 445                 return;
 446
 447         struct board_symmetry *s = &tree->root_symmetry;
 448         int cx = coord_x(c, b), cy = coord_y(c, b);
 449
 450         /* playground   X->h->v->d normalization
 451          * :::..        .d...
 452          * .::..        v....
 453          * ..:..        .....
 454          * .....        h...X
 455          * .....        .....  */
 456         bool flip_horiz = cx < s->x1 || cx > s->x2;
 457         bool flip_vert = cy < s->y1 || cy > s->y2;
 458
 459         bool flip_diag = 0;
 460         if (s->d) {
 461                 bool dir = (s->type == SYM_DIAG_DOWN);
 462                 int x = dir ^ flip_horiz ^ flip_vert ? board_size(b) - 1 - cx : cx;
 463                 if (flip_vert ? x < cy : x > cy) {
 464                         flip_diag = 1;
 465                 }
 466         }
 467
 468         if (UDEBUGL(4)) {
 469                 fprintf(stderr, "%s will flip %d %d %d -> %s, sym %d (%d) -> %d (%d)\n",
 470                         coord2sstr(c, b), flip_horiz, flip_vert, flip_diag,
 471                         coord2sstr(flip_coord(b, c, flip_horiz, flip_vert, flip_diag), b),
 472                         s->type, s->d, b->symmetry.type, b->symmetry.d);
 473         }
 474         if (flip_horiz || flip_vert || flip_diag)
 475                 tree_fix_node_symmetry(b, tree->root, flip_horiz, flip_vert, flip_diag);
 476 }
 477
 478
 479 static void
 480 tree_unlink_node(struct tree_node *node)
 481 {
 482         struct tree_node *ni = node->parent;
 483         if (ni->children == node) {
 484                 ni->children = node->sibling;
 485         } else {
 486                 ni = ni->children;
 487                 while (ni->sibling != node)
 488                         ni = ni->sibling;
 489                 ni->sibling = node->sibling;
 490         }
 491         node->sibling = NULL;
 492         node->parent = NULL;
 493 }
 494
 495 void
 496 tree_delete_node(struct tree *tree, struct tree_node *node)
 497 {
 498         tree_unlink_node(node);
 499         tree_done_node(tree, node);
 500 }
 501
 502 void
 503 tree_promote_node(struct tree *tree, struct tree_node *node)
 504 {
 505         assert(node->parent == tree->root);
 506         tree_unlink_node(node);
 507         tree_done_node(tree, tree->root);
 508         tree->root = node;
 509         tree->root_color = stone_other(tree->root_color);
 510         board_symmetry_update(tree->board, &tree->root_symmetry, node->coord);
 511 }
 512
 513 bool
 514 tree_promote_at(struct tree *tree, struct board *b, coord_t c)
 515 {
 516         tree_fix_symmetry(tree, b, c);
 517
 518         for (struct tree_node *ni = tree->root->children; ni; ni = ni->sibling) {
 519                 if (ni->coord == c) {
 520                         tree_promote_node(tree, ni);
 521                         return true;
 522                 }
 523         }
 524         return false;
 525 }