uct/prior.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 "move.h"
  10 #include "random.h"
  11 #include "tactics.h"
  12 #include "uct/internal.h"
  13 #include "uct/prior.h"
  14 #include "uct/tree.h"
  15
  16 /* Applying heuristic values to the tree nodes, skewing the reading in
  17  * most interesting directions. */
  18
  19
  20 void
  21 uct_prior_even(struct uct *u, struct tree_node *node, struct prior_map *map)
  22 {
  23         /* Q_{even} */
  24         /* This may be dubious for normal UCB1 but is essential for
  25          * reading stability of RAVE, it appears. */
  26         foreach_point_and_pass(map->b) {
  27                 if (!map->consider[c])
  28                         continue;
  29                 add_prior_value(map, c, u->even_eqex / 2, u->even_eqex);
  30         } foreach_point_end;
  31 }
  32
  33 void
  34 uct_prior_eye(struct uct *u, struct tree_node *node, struct prior_map *map)
  35 {
  36         /* Discourage playing into our own eyes. However, we cannot
  37          * completely prohibit it:
  38          * #######
  39          * ...XX.#
  40          * XOOOXX#
  41          * X.OOOO#
  42          * .XXXX.# */
  43         foreach_point(map->b) {
  44                 if (!map->consider[c])
  45                         continue;
  46                 if (!board_is_one_point_eye(map->b, &c, map->to_play))
  47                         continue;
  48                 add_prior_value(map, c, -u->eqex, u->eqex);
  49         } foreach_point_end;
  50 }
  51
  52 void
  53 uct_prior_b19(struct uct *u, struct tree_node *node, struct prior_map *map)
  54 {
  55         /* Q_{b19} */
  56         /* Specific hints for 19x19 board - priors for certain edge distances. */
  57         foreach_point(map->b) {
  58                 if (!map->consider[c])
  59                         continue;
  60                 int d = coord_edge_distance(c, map->b);
  61                 if (d != 1 && d != 3)
  62                         continue;
  63                 /* The bonus applies only with no stones in immediate
  64                  * vincinity. */
  65                 if (board_stone_radar(map->b, c, 2))
  66                         continue;
  67                 /* First line: -eqex */
  68                 /* Third line: +eqex */
  69                 int v = d == 1 ? -1 : 1;
  70                 add_prior_value(map, c, v * u->b19_eqex, u->b19_eqex);
  71         } foreach_point_end;
  72 }
  73
  74 void
  75 uct_prior_grandparent(struct uct *u, struct tree_node *node, struct prior_map *map)
  76 {
  77         /* Q_{grandparent} */
  78         foreach_point_and_pass(map->b) {
  79                 if (!map->consider[c])
  80                         continue;
  81                 if (!node->parent || !node->parent->parent)
  82                         continue;
  83                 struct tree_node *gpp = node->parent->parent;
  84                 for (struct tree_node *ni = gpp->children; ni; ni = ni->sibling) {
  85                         /* Be careful not to emphasize too random results. */
  86                         if (ni->coord == node->coord && ni->u.playouts > u->gp_eqex) {
  87                                 /* We purposefuly ignore the parity. */
  88                                 map->prior[c].playouts += u->gp_eqex;
  89                                 map->prior[c].wins += u->gp_eqex * ni->u.wins / ni->u.playouts;
  90                         }
  91                 }
  92         } foreach_point_end;
  93 }
  94
  95 void
  96 uct_prior_playout(struct uct *u, struct tree_node *node, struct prior_map *map)
  97 {
  98         /* Q_{playout-policy} */
  99         if (u->playout->assess)
 100                 u->playout->assess(u->playout, map, u->policy_eqex);
 101 }
 102
 103 void
 104 uct_prior(struct uct *u, struct tree_node *node, struct prior_map *map)
 105 {
 106         if (u->even_eqex)
 107                 uct_prior_even(u, node, map);
 108         uct_prior_eye(u, node, map);
 109         if (u->b19_eqex)
 110                 uct_prior_b19(u, node, map);
 111         if (u->gp_eqex)
 112                 uct_prior_grandparent(u, node, map);
 113         if (u->policy_eqex)
 114                 uct_prior_playout(u, node, map);
 115 }