uct/internal.h

   1 #ifndef ZZGO_UCT_INTERNAL_H
   2 #define ZZGO_UCT_INTERNAL_H
   3
   4 /* Internal UCT structures */
   5
   6 #include "debug.h"
   7 #include "distributed/distributed.h"
   8 #include "move.h"
   9 #include "ownermap.h"
  10 #include "playout.h"
  11 #include "stats.h"
  12
  13 struct tree;
  14 struct tree_node;
  15 struct uct_policy;
  16 struct uct_prior;
  17 struct uct_dynkomi;
  18
  19 /* How big proportion of ownermap counts must be of one color to consider
  20  * the point sure. */
  21 #define GJ_THRES        0.8
  22 /* How many games to consider at minimum before judging groups. */
  23 #define GJ_MINGAMES     500
  24
  25 /* Distributed stats for each child of the root node. */
  26 struct node_stats {
  27         struct move_stats2 last_sent_own;
  28         struct move_stats2 added_from_others;
  29         struct tree_node *node;
  30 };
  31
  32 /* Internal engine state. */
  33 struct uct {
  34         int debug_level;
  35         int games, gamelen;
  36         float resign_ratio;
  37         float loss_threshold;
  38         double best2_ratio, bestr_ratio;
  39         bool pass_all_alive;
  40         bool territory_scoring;
  41         int expand_p;
  42         bool playout_amaf, playout_amaf_nakade;
  43         bool amaf_prior;
  44         int playout_amaf_cutoff;
  45         int dumpthres;
  46         int force_seed;
  47         bool no_book;
  48         bool fast_alloc;
  49         unsigned long max_tree_size;
  50         int mercymin;
  51
  52         int threads;
  53         enum uct_thread_model {
  54                 TM_ROOT, /* Root parallelization. */
  55                 TM_TREE, /* Tree parallelization w/o virtual loss. */
  56                 TM_TREEVL, /* Tree parallelization with virtual loss. */
  57         } thread_model;
  58         bool parallel_tree;
  59         bool virtual_loss;
  60         bool pondering_opt; /* User wants pondering */
  61         bool pondering; /* Actually pondering now */
  62         bool slave; /* Act as slave in distributed engine. */
  63         enum stone my_color;
  64
  65         int fuseki_end;
  66         int yose_start;
  67
  68         int dynkomi_mask;
  69         int dynkomi_interval;
  70         struct uct_dynkomi *dynkomi;
  71
  72         float val_scale;
  73         int val_points;
  74         bool val_extra;
  75
  76         int random_policy_chance;
  77         int local_tree;
  78         int tenuki_d;
  79         float local_tree_aging;
  80         bool local_tree_allseq;
  81         /* Playout-localtree integration. */
  82         bool local_tree_playout; // can be true only if ELO playout
  83         bool local_tree_pseqroot;
  84
  85         char *banner;
  86
  87         struct uct_policy *policy;
  88         struct uct_policy *random_policy;
  89         struct playout_policy *playout;
  90         struct uct_prior *prior;
  91
  92         /* Used within frame of single genmove. */
  93         struct board_ownermap ownermap;
  94         /* Used for coordination among slaves of the distributed engine. */
  95         struct node_stats *stats;
  96         int played_own;
  97         int played_all; /* games played by all slaves */
  98
  99         /* Game state - maintained by setup_state(), reset_state(). */
 100         struct tree *t;
 101 };
 102
 103 #define UDEBUGL(n) DEBUGL_(u->debug_level, n)
 104
 105 bool uct_pass_is_safe(struct uct *u, struct board *b, enum stone color, bool pass_all_alive);
 106
 107 void uct_prepare_move(struct uct *u, struct board *b, enum stone color);
 108 void uct_genmove_setup(struct uct *u, struct board *b, enum stone color);
 109 void uct_pondering_stop(struct uct *u);
 110
 111
 112 /* This is the state used for descending the tree; we use this wrapper
 113  * structure in order to be able to easily descend in multiple trees
 114  * in parallel (e.g. main tree and local tree) or compute cummulative
 115  * "path value" throughout the tree descent. */
 116 struct uct_descent {
 117         /* Active tree nodes: */
 118         struct tree_node *node; /* Main tree. */
 119         struct tree_node *lnode; /* Local tree. */
 120         /* Value of main tree node (with all value factors, but unbiased
 121          * - without exploration factor), from black's perspective. */
 122         struct move_stats value;
 123 };
 124
 125
 126 typedef struct tree_node *(*uctp_choose)(struct uct_policy *p, struct tree_node *node, struct board *b, enum stone color, coord_t exclude);
 127 typedef float (*uctp_evaluate)(struct uct_policy *p, struct tree *tree, struct uct_descent *descent, int parity);
 128 typedef void (*uctp_descend)(struct uct_policy *p, struct tree *tree, struct uct_descent *descent, int parity, bool allow_pass);
 129 typedef void (*uctp_winner)(struct uct_policy *p, struct tree *tree, struct uct_descent *descent);
 130 typedef void (*uctp_prior)(struct uct_policy *p, struct tree *tree, struct tree_node *node, struct board *b, enum stone color, int parity);
 131 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);
 132
 133 struct uct_policy {
 134         struct uct *uct;
 135         uctp_choose choose;
 136         uctp_winner winner;
 137         uctp_evaluate evaluate;
 138         uctp_descend descend;
 139         uctp_update update;
 140         uctp_prior prior;
 141         bool wants_amaf;
 142         void *data;
 143 };
 144
 145 #endif