uct/internal.h

   1 #ifndef ZZGO_UCT_INTERNAL_H
   2 #define ZZGO_UCT_INTERNAL_H
   3
   4 #include <signal.h> // sig_atomic_t
   5
   6 #include "debug.h"
   7 #include "move.h"
   8 #include "ownermap.h"
   9 #include "playout.h"
  10
  11 struct tree;
  12 struct tree_node;
  13 struct uct_policy;
  14 struct uct_prior;
  15
  16 /* Internal UCT structures */
  17
  18
  19 /* Internal engine state. */
  20 struct uct {
  21         int debug_level;
  22         int games, gamelen;
  23         float resign_ratio;
  24         float loss_threshold;
  25         double best2_ratio, bestr_ratio;
  26         bool pass_all_alive;
  27         int expand_p;
  28         bool playout_amaf, playout_amaf_nakade;
  29         bool amaf_prior;
  30         int playout_amaf_cutoff;
  31         int dumpthres;
  32         int force_seed;
  33         bool no_book;
  34         bool fast_alloc;
  35         unsigned long max_tree_size;
  36         int mercymin;
  37
  38         int threads;
  39         enum uct_thread_model {
  40                 TM_ROOT, /* Root parallelization. */
  41                 TM_TREE, /* Tree parallelization w/o virtual loss. */
  42                 TM_TREEVL, /* Tree parallelization with virtual loss. */
  43         } thread_model;
  44         bool parallel_tree;
  45         bool virtual_loss;
  46         bool pondering_opt; /* User wants pondering */
  47         bool pondering; /* Actually pondering now */
  48
  49         int fuseki_end;
  50         int yose_start;
  51
  52         int dynkomi;
  53         int dynkomi_mask;
  54
  55         float val_scale;
  56         int val_points;
  57         bool val_extra;
  58
  59         int random_policy_chance;
  60         int root_heuristic;
  61
  62         char *banner;
  63
  64         struct uct_policy *policy;
  65         struct uct_policy *random_policy;
  66         struct playout_policy *playout;
  67         struct uct_prior *prior;
  68
  69         /* Used within frame of single genmove. */
  70         struct board_ownermap ownermap;
  71
  72         /* Game state - maintained by setup_state(), reset_state(). */
  73         struct tree *t;
  74 };
  75
  76 #define UDEBUGL(n) DEBUGL_(u->debug_level, n)
  77
  78 extern volatile sig_atomic_t uct_halt;
  79 extern __thread int thread_id;
  80
  81 bool uct_pass_is_safe(struct uct *u, struct board *b, enum stone color, bool pass_all_alive);
  82
  83
  84 typedef struct tree_node *(*uctp_choose)(struct uct_policy *p, struct tree_node *node, struct board *b, enum stone color, coord_t exclude);
  85 typedef struct tree_node *(*uctp_winner)(struct uct_policy *p, struct tree *tree, struct tree_node *node);
  86 typedef float (*uctp_evaluate)(struct uct_policy *p, void **state, struct tree *tree, struct tree_node *node, int parity);
  87 typedef struct tree_node *(*uctp_descend)(struct uct_policy *p, void **state, struct tree *tree, struct tree_node *node, int parity, bool allow_pass);
  88 typedef void (*uctp_prior)(struct uct_policy *p, struct tree *tree, struct tree_node *node, struct board *b, enum stone color, int parity);
  89 typedef void (*uctp_update)(struct uct_policy *p, struct tree *tree, struct tree_node *node, enum stone node_color, enum stone player_color, struct playout_amafmap *amaf, float result);
  90
  91 struct uct_policy {
  92         struct uct *uct;
  93         uctp_choose choose;
  94         uctp_winner winner;
  95         uctp_evaluate evaluate;
  96         uctp_descend descend;
  97         uctp_update update;
  98         uctp_prior prior;
  99         bool wants_amaf;
 100         void *data;
 101 };
 102
 103 #endif