playout.c

   1 #include <assert.h>
   2 #include <math.h>
   3 #include <stdio.h>
   4 #include <stdlib.h>
   5 #include <string.h>
   6
   7 #include "board.h"
   8 #include "debug.h"
   9 #include "engine.h"
  10 #include "move.h"
  11 #include "ownermap.h"
  12 #include "playout.h"
  13 #include "probdist.h"
  14
  15
  16 static coord_t
  17 try_probdist_move(struct board *b, enum stone color, struct playout_setup *setup)
  18 {
  19         /* First try probability distribution provided by
  20          * the engine for this move. */
  21         struct probdist pd;
  22         probdist_init(&pd, board_size2(b));
  23
  24         setup->probdist(setup, &pd, b);
  25         if (pd.moves[0] >= pd.total - __FLT_EPSILON__) {
  26                 probdist_done(&pd);
  27                 return pass;
  28         }
  29
  30         coord_t coord = probdist_pick(&pd);
  31         probdist_done(&pd);
  32
  33         /* If the pick is invalid, defer to policy. */
  34         if (!coord || is_pass(coord))
  35                 return pass;
  36         struct move m = { .coord = coord, .color = color };
  37         if (!board_is_valid_move(b, &m))
  38                 return pass;
  39
  40         return coord;
  41 }
  42
  43 int
  44 play_random_game(struct playout_setup *setup,
  45                  struct board *b, enum stone starting_color,
  46                  struct playout_amafmap *amafmap,
  47                  struct board_ownermap *ownermap,
  48                  struct playout_policy *policy)
  49 {
  50         assert(setup && policy);
  51
  52         int gamelen = setup->gamelen - b->moves;
  53         if (gamelen < 10)
  54                 gamelen = 10;
  55
  56         enum stone color = starting_color;
  57
  58         int passes = is_pass(b->last_move.coord) && b->moves > 0;
  59
  60         while (gamelen-- && passes < 2) {
  61                 coord_t coord = pass;
  62
  63                 if (setup->probdist) {
  64                         coord = try_probdist_move(b, color, setup);
  65                 }
  66
  67                 if (is_pass(coord)) {
  68                         /* Defer to policy move choice. */
  69                         coord = policy->choose(policy, b, color);
  70                 }
  71
  72                 if (is_pass(coord)) {
  73 play_random:
  74                         /* Defer to uniformly random move choice. */
  75                         board_play_random(b, color, &coord, (ppr_permit) policy->permit, policy);
  76
  77                 } else {
  78                         struct move m;
  79                         m.coord = coord; m.color = color;
  80                         if (board_play(b, &m) < 0) {
  81                                 if (DEBUGL(8)) {
  82                                         fprintf(stderr, "Pre-picked move %d,%d is ILLEGAL:\n",
  83                                                 coord_x(coord, b), coord_y(coord, b));
  84                                         board_print(b, stderr);
  85                                 }
  86                                 goto play_random;
  87                         }
  88                 }
  89
  90 #if 0
  91                 /* For UCT, superko test here is downright harmful since
  92                  * in superko-likely situation we throw away literally
  93                  * 95% of our playouts; UCT will deal with this fine by
  94                  * itself. */
  95                 if (unlikely(b->superko_violation)) {
  96                         /* We ignore superko violations that are suicides. These
  97                          * are common only at the end of the game and are
  98                          * rather harmless. (They will not go through as a root
  99                          * move anyway.) */
 100                         if (group_at(b, coord)) {
 101                                 if (DEBUGL(3)) {
 102                                         fprintf(stderr, "Superko fun at %d,%d in\n", coord_x(coord, b), coord_y(coord, b));
 103                                         if (DEBUGL(4))
 104                                                 board_print(b, stderr);
 105                                 }
 106                                 return 0;
 107                         } else {
 108                                 if (DEBUGL(6)) {
 109                                         fprintf(stderr, "Ignoring superko at %d,%d in\n", coord_x(coord, b), coord_y(coord, b));
 110                                         board_print(b, stderr);
 111                                 }
 112                                 b->superko_violation = false;
 113                         }
 114                 }
 115 #endif
 116
 117                 if (DEBUGL(7)) {
 118                         fprintf(stderr, "%s %s\n", stone2str(color), coord2sstr(coord, b));
 119                         if (DEBUGL(8))
 120                                 board_print(b, stderr);
 121                 }
 122
 123                 if (unlikely(is_pass(coord))) {
 124                         passes++;
 125                 } else {
 126                         /* We don't care about nakade counters, since we want
 127                          * to avoid taking pre-nakade moves into account only
 128                          * if they happenned in the tree before nakade nodes;
 129                          * but this is always out of the tree. */
 130                         if (amafmap) {
 131                                 if (amafmap->map[coord] == S_NONE || amafmap->map[coord] == color)
 132                                         amafmap->map[coord] = color;
 133                                 else if (amafmap->record_nakade)
 134                                         amaf_op(amafmap->map[coord], +);
 135                                 amafmap->game[amafmap->gamelen].coord = coord;
 136                                 amafmap->game[amafmap->gamelen].color = color;
 137                                 amafmap->gamelen++;
 138                                 assert(amafmap->gamelen < sizeof(amafmap->game) / sizeof(amafmap->game[0]));
 139                         }
 140
 141                         passes = 0;
 142                 }
 143
 144                 color = stone_other(color);
 145         }
 146
 147         float score = board_fast_score(b);
 148         int result = (starting_color == S_WHITE ? score * 2 : - (score * 2));
 149
 150         if (DEBUGL(6)) {
 151                 fprintf(stderr, "Random playout result: %d (W %f)\n", result, score);
 152                 if (DEBUGL(7))
 153                         board_print(b, stderr);
 154         }
 155
 156         if (ownermap)
 157                 board_ownermap_fill(ownermap, b);
 158
 159         return result;
 160 }