playout.c

   1 #define DEBUG
   2 #include <assert.h>
   3 #include <math.h>
   4 #include <stdio.h>
   5 #include <stdlib.h>
   6 #include <string.h>
   7
   8 #include "board.h"
   9 #include "debug.h"
  10 #include "engine.h"
  11 #include "move.h"
  12 #include "ownermap.h"
  13 #include "playout.h"
  14
  15 #define PLDEBUGL(n) DEBUGL_(policy->debug_level, n)
  16
  17
  18 int
  19 play_random_game(struct playout_setup *setup,
  20                  struct board *b, enum stone starting_color,
  21                  struct playout_amafmap *amafmap,
  22                  struct board_ownermap *ownermap,
  23                  struct playout_policy *policy)
  24 {
  25         assert(setup && policy);
  26
  27         int gamelen = setup->gamelen - b->moves;
  28         if (gamelen < 10)
  29                 gamelen = 10;
  30
  31         if (policy->setboard)
  32                 policy->setboard(policy, b);
  33
  34         enum stone color = starting_color;
  35
  36         int passes = is_pass(b->last_move.coord) && b->moves > 0;
  37
  38         while (gamelen-- && passes < 2) {
  39                 coord_t coord;
  40                 coord = policy->choose(policy, b, color);
  41
  42                 if (is_pass(coord)) {
  43 play_random:
  44                         /* Defer to uniformly random move choice. */
  45                         /* This must never happen if the policy is tracking
  46                          * internal board state, obviously. */
  47                         assert(!policy->setboard);
  48                         board_play_random(b, color, &coord, (ppr_permit) policy->permit, policy);
  49
  50                 } else {
  51                         struct move m;
  52                         m.coord = coord; m.color = color;
  53                         if (board_play(b, &m) < 0) {
  54                                 if (PLDEBUGL(4)) {
  55                                         fprintf(stderr, "Pre-picked move %d,%d is ILLEGAL:\n",
  56                                                 coord_x(coord, b), coord_y(coord, b));
  57                                         board_print(b, stderr);
  58                                 }
  59                                 goto play_random;
  60                         }
  61                 }
  62
  63 #if 0
  64                 /* For UCT, superko test here is downright harmful since
  65                  * in superko-likely situation we throw away literally
  66                  * 95% of our playouts; UCT will deal with this fine by
  67                  * itself. */
  68                 if (unlikely(b->superko_violation)) {
  69                         /* We ignore superko violations that are suicides. These
  70                          * are common only at the end of the game and are
  71                          * rather harmless. (They will not go through as a root
  72                          * move anyway.) */
  73                         if (group_at(b, coord)) {
  74                                 if (DEBUGL(3)) {
  75                                         fprintf(stderr, "Superko fun at %d,%d in\n", coord_x(coord, b), coord_y(coord, b));
  76                                         if (DEBUGL(4))
  77                                                 board_print(b, stderr);
  78                                 }
  79                                 return 0;
  80                         } else {
  81                                 if (DEBUGL(6)) {
  82                                         fprintf(stderr, "Ignoring superko at %d,%d in\n", coord_x(coord, b), coord_y(coord, b));
  83                                         board_print(b, stderr);
  84                                 }
  85                                 b->superko_violation = false;
  86                         }
  87                 }
  88 #endif
  89
  90                 if (PLDEBUGL(7)) {
  91                         fprintf(stderr, "%s %s\n", stone2str(color), coord2sstr(coord, b));
  92                         if (PLDEBUGL(8))
  93                                 board_print(b, stderr);
  94                 }
  95
  96                 if (unlikely(is_pass(coord))) {
  97                         passes++;
  98                 } else {
  99                         /* We don't care about nakade counters, since we want
 100                          * to avoid taking pre-nakade moves into account only
 101                          * if they happenned in the tree before nakade nodes;
 102                          * but this is always out of the tree. */
 103                         if (amafmap) {
 104                                 if (amafmap->map[coord] == S_NONE || amafmap->map[coord] == color)
 105                                         amafmap->map[coord] = color;
 106                                 else if (amafmap->record_nakade)
 107                                         amaf_op(amafmap->map[coord], +);
 108                                 amafmap->game[amafmap->gamelen].coord = coord;
 109                                 amafmap->game[amafmap->gamelen].color = color;
 110                                 amafmap->gamelen++;
 111                                 assert(amafmap->gamelen < sizeof(amafmap->game) / sizeof(amafmap->game[0]));
 112                         }
 113
 114                         passes = 0;
 115                 }
 116
 117                 if (setup->mercymin && abs(b->captures[S_BLACK] - b->captures[S_WHITE]) > setup->mercymin)
 118                         break;
 119
 120                 color = stone_other(color);
 121         }
 122
 123         float score = board_fast_score(b);
 124         int result = (starting_color == S_WHITE ? score * 2 : - (score * 2));
 125
 126         if (DEBUGL(6)) {
 127                 fprintf(stderr, "Random playout result: %d (W %f)\n", result, score);
 128                 if (DEBUGL(7))
 129                         board_print(b, stderr);
 130         }
 131
 132         if (ownermap)
 133                 board_ownermap_fill(ownermap, b);
 134
 135         if (b->ps)
 136                 free(b->ps);
 137
 138         return result;
 139 }