From cdc05ff983c1713795a116fd8f7b6647e95ddf6b Mon Sep 17 00:00:00 2001
From: Petr Baudis <pasky@ucw.cz>
Date: Sun, 4 Oct 2009 02:38:29 +0200
Subject: [PATCH] UCB1TUNED: Remove bitrotten policy that was never working
 well

---
 uct/policy/Makefile    |  2 +-
 uct/policy/ucb1tuned.c | 90 --------------------------------------------------
 uct/uct.c              |  3 --
 3 files changed, 1 insertion(+), 94 deletions(-)
 delete mode 100644 uct/policy/ucb1tuned.c

diff --git a/uct/policy/Makefile b/uct/policy/Makefile
index 0acf99b..6d6639e 100644
--- a/uct/policy/Makefile
+++ b/uct/policy/Makefile
@@ -1,5 +1,5 @@
 INCLUDES=-I../..
-OBJS=ucb1.o ucb1tuned.o ucb1amaf.o
+OBJS=ucb1.o ucb1amaf.o
 
 all: uctpolicy.a
 uctpolicy.a: $(OBJS)
diff --git a/uct/policy/ucb1tuned.c b/uct/policy/ucb1tuned.c
deleted file mode 100644
index 10c55d6..0000000
--- a/uct/policy/ucb1tuned.c
+++ /dev/null
@@ -1,90 +0,0 @@
-#include <assert.h>
-#include <math.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-#include "board.h"
-#include "debug.h"
-#include "move.h"
-#include "uct/internal.h"
-#include "uct/tree.h"
-
-/* This implements the UCB1-TUNED policy. */
-
-struct ucb1_policy_tuned {
-	/* This is what the Modification of UCT with Patterns in Monte Carlo Go
-	 * paper calls 'p'. Original UCB has this on 2, but this seems to
-	 * produce way too wide searches; reduce this to get deeper and
-	 * narrower readouts - try 0.2. */
-	float explore_p;
-	float fpu;
-};
-
-
-struct tree_node *ucb1_choose(struct uct_policy *p, struct tree_node *node, struct board *b, enum stone color);
-
-struct tree_node *
-ucb1tuned_descend(struct uct_policy *p, struct tree *tree, struct tree_node *node, int parity, bool allow_pass)
-{
-	struct ucb1_policy_tuned *b = p->data;
-	float xpl = log(node->u.playouts) * b->explore_p;
-
-	struct tree_node *nbest = node->children;
-	float best_urgency = -9999;
-	for (struct tree_node *ni = node->children; ni; ni = ni->sibling) {
-		/* Do not consider passing early. */
-		if (likely(!allow_pass) && unlikely(is_pass(ni->coord)))
-			continue;
-		float xpl_loc = (ni->u.value - ni->u.value * ni->u.value);
-		if (tree_parity(tree, parity) < 0) xpl_loc = 1 - xpl_loc;
-		xpl_loc += sqrt(xpl / ni->u.playouts);
-		if (xpl_loc > 1.0/4) xpl_loc = 1.0/4;
-		float urgency = tree_node_get_value(tree, ni, u, parity) + sqrt(xpl * xpl_loc / ni->u.playouts);
-		if (urgency > best_urgency) {
-			best_urgency = urgency;
-			nbest = ni;
-		}
-	}
-	return nbest;
-}
-
-void ucb1_update(struct uct_policy *p, struct tree *tree, struct tree_node *node, enum stone node_color, enum stone player_color, struct playout_amafmap *map, int result);
-
-
-struct uct_policy *
-policy_ucb1tuned_init(struct uct *u, char *arg)
-{
-	struct uct_policy *p = calloc(1, sizeof(*p));
-	struct ucb1_policy_tuned *b = calloc(1, sizeof(*b));
-	p->uct = u;
-	p->data = b;
-	p->descend = ucb1tuned_descend;
-	p->choose = ucb1_choose;
-	p->update = ucb1_update;
-
-	b->explore_p = 0.2;
-	b->fpu = INFINITY;
-
-	if (arg) {
-		char *optspec, *next = arg;
-		while (*next) {
-			optspec = next;
-			next += strcspn(next, ":");
-			if (*next) { *next++ = 0; } else { *next = 0; }
-
-			char *optname = optspec;
-			char *optval = strchr(optspec, '=');
-			if (optval) *optval++ = 0;
-
-			if (!strcasecmp(optname, "explore_p")) {
-				b->explore_p = atof(optval);
-			} else {
-				fprintf(stderr, "ucb1tuned: Invalid policy argument %s or missing value\n", optname);
-				exit(1);
-			}
-		}
-	}
-
-	return p;
-}
diff --git a/uct/uct.c b/uct/uct.c
index 87d93ff..1d26be9 100644
--- a/uct/uct.c
+++ b/uct/uct.c
@@ -20,7 +20,6 @@
 #include "uct/uct.h"
 
 struct uct_policy *policy_ucb1_init(struct uct *u, char *arg);
-struct uct_policy *policy_ucb1tuned_init(struct uct *u, char *arg);
 struct uct_policy *policy_ucb1amaf_init(struct uct *u, char *arg);
 
 
@@ -570,8 +569,6 @@ uct_state_init(char *arg)
 					*policyarg++ = 0;
 				if (!strcasecmp(optval, "ucb1")) {
 					u->policy = policy_ucb1_init(u, policyarg);
-				} else if (!strcasecmp(optval, "ucb1tuned")) {
-					u->policy = policy_ucb1tuned_init(u, policyarg);
 				} else if (!strcasecmp(optval, "ucb1amaf")) {
 					u->policy = policy_ucb1amaf_init(u, policyarg);
 				} else {
-- 
2.11.4.GIT