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/prior.h"
  16 #include "uct/tree.h"
  17
  18
  19 static struct tree_node *
  20 tree_init_node(struct tree *t, coord_t coord, int depth)
  21 {
  22         struct tree_node *n = calloc(1, sizeof(*n));
  23         n->coord = coord;
  24         n->depth = depth;
  25         static long c = 1000000;
  26         n->hash = c++;
  27         if (depth > t->max_depth)
  28                 t->max_depth = depth;
  29         return n;
  30 }
  31
  32 struct tree *
  33 tree_init(struct board *board, enum stone color)
  34 {
  35         struct tree *t = calloc(1, sizeof(*t));
  36         t->board = board;
  37         /* The root PASS move is only virtual, we never play it. */
  38         t->root = tree_init_node(t, pass, 0);
  39         t->root_symmetry = board->symmetry;
  40         t->root_color = stone_other(color); // to research black moves, root will be white
  41         return t;
  42 }
  43
  44
  45 static void
  46 tree_done_node(struct tree *t, struct tree_node *n)
  47 {
  48         struct tree_node *ni = n->children;
  49         while (ni) {
  50                 struct tree_node *nj = ni->sibling;
  51                 tree_done_node(t, ni);
  52                 ni = nj;
  53         }
  54         free(n);
  55 }
  56
  57 void
  58 tree_done(struct tree *t)
  59 {
  60         tree_done_node(t, t->root);
  61         free(t);
  62 }
  63
  64
  65 static void
  66 tree_node_dump(struct tree *tree, struct tree_node *node, int l, int thres)
  67 {
  68         for (int i = 0; i < l; i++) fputc(' ', stderr);
  69         int children = 0;
  70         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
  71                 children++;
  72         /* We use 1 as parity, since for all nodes we want to know the
  73          * win probability of _us_, not the node color. */
  74         fprintf(stderr, "[%s] %f (%d/%d playouts [prior %d/%d amaf %d/%d]; hints %x; %d children) <%lld>\n",
  75                 coord2sstr(node->coord, tree->board),
  76                 tree_node_get_value(tree, node, u, 1),
  77                 tree_node_get_wins(tree, node, u, 1), node->u.playouts,
  78                 tree_node_get_wins(tree, node, prior, 1), node->prior.playouts,
  79                 tree_node_get_wins(tree, node, amaf, 1), node->amaf.playouts,
  80                 node->hints, children, node->hash);
  81
  82         /* Print nodes sorted by #playouts. */
  83
  84         struct tree_node *nbox[1000]; int nboxl = 0;
  85         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
  86                 if (ni->u.playouts > thres)
  87                         nbox[nboxl++] = ni;
  88
  89         while (true) {
  90                 int best = -1;
  91                 for (int i = 0; i < nboxl; i++)
  92                         if (nbox[i] && (best < 0 || nbox[i]->u.playouts > nbox[best]->u.playouts))
  93                                 best = i;
  94                 if (best < 0)
  95                         break;
  96                 tree_node_dump(tree, nbox[best], l + 1, /* node->u.value < 0.1 ? 0 : */ thres);
  97                 nbox[best] = NULL;
  98         }
  99 }
 100
 101 void
 102 tree_dump(struct tree *tree, int thres)
 103 {
 104         if (thres && tree->root->u.playouts / thres > 100) {
 105                 /* Be a bit sensible about this; the opening book can create
 106                  * huge dumps at first. */
 107                 thres = tree->root->u.playouts / 100 * (thres < 1000 ? 1 : thres / 1000);
 108         }
 109         tree_node_dump(tree, tree->root, 0, thres);
 110 }
 111
 112
 113 static char *
 114 tree_book_name(struct board *b)
 115 {
 116         static char buf[256];
 117         if (b->handicap > 0) {
 118                 sprintf(buf, "uctbook-%d-%02.01f-h%d.pachitree", b->size - 2, b->komi, b->handicap);
 119         } else {
 120                 sprintf(buf, "uctbook-%d-%02.01f.pachitree", b->size - 2, b->komi);
 121         }
 122         return buf;
 123 }
 124
 125 static void
 126 tree_node_save(FILE *f, struct tree_node *node, int thres)
 127 {
 128         fputc(1, f);
 129         fwrite(((void *) node) + offsetof(struct tree_node, depth),
 130                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 131                1, f);
 132
 133         if (node->u.playouts >= thres)
 134                 for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 135                         tree_node_save(f, ni, thres);
 136
 137         fputc(0, f);
 138 }
 139
 140 void
 141 tree_save(struct tree *tree, struct board *b, int thres)
 142 {
 143         char *filename = tree_book_name(b);
 144         FILE *f = fopen(filename, "wb");
 145         if (!f) {
 146                 perror("fopen");
 147                 return;
 148         }
 149         tree_node_save(f, tree->root, thres);
 150         fputc(0, f);
 151         fclose(f);
 152 }
 153
 154
 155 void
 156 tree_node_load(FILE *f, struct tree_node *node, int *num)
 157 {
 158         (*num)++;
 159
 160         fread(((void *) node) + offsetof(struct tree_node, depth),
 161                sizeof(struct tree_node) - offsetof(struct tree_node, depth),
 162                1, f);
 163
 164         /* Keep values in sane scale, otherwise we start overflowing.
 165          * We may go slow here but we must be careful about not getting
 166          * too huge integers.*/
 167 #define MAX_PLAYOUTS    10000000
 168         if (node->u.playouts > MAX_PLAYOUTS) {
 169                 int over = node->u.playouts - MAX_PLAYOUTS;
 170                 node->u.wins -= ((double) node->u.wins / node->u.playouts) * over;
 171                 node->u.playouts = MAX_PLAYOUTS;
 172         }
 173         if (node->amaf.playouts > MAX_PLAYOUTS) {
 174                 int over = node->amaf.playouts - MAX_PLAYOUTS;
 175                 node->amaf.wins -= ((double) node->amaf.wins / node->amaf.playouts) * over;
 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, bool amaf_prior)
 242 {
 243         dest->hints |= src->hints;
 244
 245         /* Merge the children, both are coord-sorted lists. */
 246         struct tree_node *di = dest->children, **dref = &dest->children;
 247         struct tree_node *si = src->children, **sref = &src->children;
 248         while (di && si) {
 249                 if (di->coord != si->coord) {
 250                         /* src has some extra items or misses di */
 251                         struct tree_node *si2 = si->sibling;
 252                         while (si2 && di->coord != si2->coord) {
 253                                 si2 = si2->sibling;
 254                         }
 255                         if (!si2)
 256                                 goto next_di; /* src misses di, move on */
 257                         /* chain the extra [si,si2) items before di */
 258                         (*dref) = si;
 259                         while (si->sibling != si2) {
 260                                 si->parent = dest;
 261                                 si = si->sibling;
 262                         }
 263                         si->parent = dest;
 264                         si->sibling = di;
 265                         si = si2;
 266                         (*sref) = si;
 267                 }
 268                 /* Matching nodes - recurse... */
 269                 tree_node_merge(di, si, amaf_prior);
 270                 /* ...and move on. */
 271                 sref = &si->sibling; si = si->sibling;
 272 next_di:
 273                 dref = &di->sibling; di = di->sibling;
 274         }
 275         if (si) {
 276                 /* Some outstanding nodes are left on src side, rechain
 277                  * them to dst. */
 278                 (*dref) = si;
 279                 while (si) {
 280                         si->parent = dest;
 281                         si = si->sibling;
 282                 }
 283                 (*sref) = NULL;
 284         }
 285
 286         /* Priors should be constant. */
 287         assert(dest->prior.playouts == src->prior.playouts && dest->prior.wins == src->prior.wins);
 288
 289         dest->amaf.playouts += src->amaf.playouts;
 290         dest->amaf.wins += src->amaf.wins;
 291         tree_update_node_value(dest, amaf_prior);
 292
 293         dest->u.playouts += src->u.playouts;
 294         dest->u.wins += src->u.wins;
 295         tree_update_node_rvalue(dest, amaf_prior);
 296 }
 297
 298 /* Merge two trees built upon the same board. Note that the operation is
 299  * destructive on src. */
 300 void
 301 tree_merge(struct tree *dest, struct tree *src, bool amaf_prior)
 302 {
 303         if (src->max_depth > dest->max_depth)
 304                 dest->max_depth = src->max_depth;
 305         tree_node_merge(dest->root, src->root, amaf_prior);
 306 }
 307
 308
 309 static void
 310 tree_node_normalize(struct tree_node *node, int factor)
 311 {
 312         for (struct tree_node *ni = node->children; ni; ni = ni->sibling)
 313                 tree_node_normalize(ni, factor);
 314
 315 #define normalize(s1, s2, t) node->s2.t = node->s1.t + (node->s2.t - node->s1.t) / factor;
 316         normalize(pamaf, amaf, playouts);
 317         normalize(pamaf, amaf, wins);
 318         memcpy(&node->pamaf, &node->amaf, sizeof(node->amaf));
 319
 320         normalize(pu, u, playouts);
 321         normalize(pu, u, wins);
 322         memcpy(&node->pu, &node->u, sizeof(node->u));
 323 #undef normalize
 324 }
 325
 326 /* Normalize a tree, dividing the amaf and u values by given
 327  * factor; otherwise, simulations run in independent threads
 328  * two trees built upon the same board. To correctly handle
 329  * results taken from previous simulation run, they are backed
 330  * up in tree. */
 331 void
 332 tree_normalize(struct tree *tree, int factor)
 333 {
 334         tree_node_normalize(tree->root, factor);
 335 }
 336
 337
 338 /* Tree symmetry: When possible, we will localize the tree to a single part
 339  * of the board in tree_expand_node() and possibly flip along symmetry axes
 340  * to another part of the board in tree_promote_at(). We follow b->symmetry
 341  * guidelines here. */
 342
 343
 344 void
 345 tree_expand_node(struct tree *t, struct tree_node *node, struct board *b, enum stone color, int radar, struct uct *u, int parity)
 346 {
 347         struct tree_node *ni = tree_init_node(t, pass, node->depth + 1);
 348         ni->parent = node; node->children = ni;
 349         uct_prior(u, t, ni, b, color, parity);
 350
 351         /* The loop considers only the symmetry playground. */
 352         if (UDEBUGL(6)) {
 353                 fprintf(stderr, "expanding %s within [%d,%d],[%d,%d] %d-%d\n",
 354                                 coord2sstr(node->coord, b),
 355                                 b->symmetry.x1, b->symmetry.y1,
 356                                 b->symmetry.x2, b->symmetry.y2,
 357                                 b->symmetry.type, b->symmetry.d);
 358         }
 359         for (int i = b->symmetry.x1; i <= b->symmetry.x2; i++) {
 360                 for (int j = b->symmetry.y1; j <= b->symmetry.y2; j++) {
 361                         if (b->symmetry.d) {
 362                                 int x = b->symmetry.type == SYM_DIAG_DOWN ? board_size(b) - 1 - i : i;
 363                                 if (x > j) {
 364                                         if (UDEBUGL(7))
 365                                                 fprintf(stderr, "drop %d,%d\n", i, j);
 366                                         continue;
 367                                 }
 368                         }
 369
 370                         coord_t c = coord_xy_otf(i, j, t->board);
 371                         if (board_at(b, c) != S_NONE)
 372                                 continue;
 373                         assert(c != node->coord); // I have spotted "C3 C3" in some sequence...
 374                         /* This looks very useful on large boards - weeds out huge amount of crufty moves. */
 375                         if (b->hash /* not empty board */ && radar && !board_stone_radar(b, c, radar))
 376                                 continue;
 377
 378                         struct tree_node *nj = tree_init_node(t, c, node->depth + 1);
 379                         nj->parent = node; ni->sibling = nj; ni = nj;
 380
 381                         uct_prior(u, 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 }