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