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         bool territory_scoring;
  28         int expand_p;
  29         bool playout_amaf, playout_amaf_nakade;
  30         bool amaf_prior;
  31         int playout_amaf_cutoff;
  32         int dumpthres;
  33         int force_seed;
  34         bool no_book;
  35         bool fast_alloc;
  36         unsigned long max_tree_size;
  37         int mercymin;
  38
  39         int threads;
  40         enum uct_thread_model {
  41                 TM_ROOT, /* Root parallelization. */
  42                 TM_TREE, /* Tree parallelization w/o virtual loss. */
  43                 TM_TREEVL, /* Tree parallelization with virtual loss. */
  44         } thread_model;
  45         bool parallel_tree;
  46         bool virtual_loss;
  47         bool pondering_opt; /* User wants pondering */
  48         bool pondering; /* Actually pondering now */
  49
  50         int fuseki_end;
  51         int yose_start;
  52
  53         int dynkomi;
  54         int dynkomi_mask;
  55         int handicap_value;
  56
  57         float val_scale;
  58         int val_points;
  59         bool val_extra;
  60
  61         int random_policy_chance;
  62         int root_heuristic;
  63
  64         char *banner;
  65
  66         struct uct_policy *policy;
  67         struct uct_policy *random_policy;
  68         struct playout_policy *playout;
  69         struct uct_prior *prior;
  70
  71         /* Used within frame of single genmove. */
  72         struct board_ownermap ownermap;
  73
  74         /* Game state - maintained by setup_state(), reset_state(). */
  75         struct tree *t;
  76 };
  77
  78 #define UDEBUGL(n) DEBUGL_(u->debug_level, n)
  79
  80 extern volatile sig_atomic_t uct_halt;
  81 extern __thread int thread_id;
  82
  83 bool uct_pass_is_safe(struct uct *u, struct board *b, enum stone color, bool pass_all_alive);
  84
  85
  86 typedef struct tree_node *(*uctp_choose)(struct uct_policy *p, struct tree_node *node, struct board *b, enum stone color, coord_t exclude);
  87 typedef struct tree_node *(*uctp_winner)(struct uct_policy *p, struct tree *tree, struct tree_node *node);
  88 typedef float (*uctp_evaluate)(struct uct_policy *p, void **state, struct tree *tree, struct tree_node *node, int parity);
  89 typedef struct tree_node *(*uctp_descend)(struct uct_policy *p, void **state, struct tree *tree, struct tree_node *node, int parity, bool allow_pass);
  90 typedef void (*uctp_prior)(struct uct_policy *p, struct tree *tree, struct tree_node *node, struct board *b, enum stone color, int parity);
  91 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);
  92
  93 struct uct_policy {
  94         struct uct *uct;
  95         uctp_choose choose;
  96         uctp_winner winner;
  97         uctp_evaluate evaluate;
  98         uctp_descend descend;
  99         uctp_update update;
 100         uctp_prior prior;
 101         bool wants_amaf;
 102         void *data;
 103 };
 104
 105 #endif