static bool
test_sar(struct board *b, char *arg)
{
enum stone color = str2stone(arg);
arg += 2;
coord_t *cc = str2coord(arg, board_size(b));
coord_t c = *cc; coord_done(cc);
arg += strcspn(arg, " ") + 1;
int eres = atoi(arg);
board_print_test(2, b);
if (DEBUGL(1))
printf("sar %s %s %d...\t", stone2str(color), coord2sstr(c, b), eres);
assert(board_at(b, c) == S_NONE);
int rres = is_bad_selfatari(b, color, c);
if (rres == eres) {
if (DEBUGL(1))
printf("OK\n");
} else {
if (debug_level <= 2) {
board_print_test(0, b);
printf("sar %s %s %d...\t", stone2str(color), coord2sstr(c, b), eres);
}
printf("FAILED (%d)\n", rres);
}
return rres == eres;
}
static bool
test_useful_ladder(struct board *b, char *arg)
{
enum stone color = str2stone(arg);
arg += 2;
coord_t *cc = str2coord(arg, board_size(b));
coord_t c = *cc; coord_done(cc);
arg += strcspn(arg, " ") + 1;
int eres = atoi(arg);
board_print_test(2, b);
if (DEBUGL(1))
printf("useful_ladder %s %s %d...\t", stone2str(color), coord2sstr(c, b), eres);
assert(board_at(b, c) == S_NONE);
group_t atari_neighbor = board_get_atari_neighbor(b, c, color);
assert(atari_neighbor);
int ladder = is_ladder(b, c, atari_neighbor, true); assert(ladder);
int rres = useful_ladder(b, atari_neighbor);
if (rres == eres) {
if (DEBUGL(1))
printf("OK\n");
} else {
if (debug_level <= 2) {
board_print_test(0, b);
printf("useful_ladder %s %s %d...\t", stone2str(color), coord2sstr(c, b), eres);
}
printf("FAILED (%d)\n", rres);
}
return (rres == eres);
}
static floating_t
linear_permove(struct uct_dynkomi *d, struct board *b, struct tree *tree)
{
struct dynkomi_linear *l = d->data;
enum stone color = d->uct->pondering ? tree->root_color : stone_other(tree->root_color);
int lmoves = l->moves[color];
floating_t extra_komi;
if (b->moves < lmoves) {
floating_t base_komi = board_effective_handicap(b, l->handicap_value[color]);
extra_komi = base_komi * (lmoves - b->moves) / lmoves;
return extra_komi;
} else {
extra_komi = floor(tree->extra_komi);
}
/* Do not take decisions on unstable value. */
if (tree->root->u.playouts < GJ_MINGAMES) return extra_komi;
floating_t my_value = tree_node_get_value(tree, 1, tree->root->u.value);
/* We normalize komi as in komi_by_value(), > 0 when winning. */
extra_komi = komi_by_color(extra_komi, color);
if (extra_komi < 0 && DEBUGL(3))
fprintf(stderr, "XXX: extra_komi %.3f < 0 (color %s tree ek %.3f)\n", extra_komi, stone2str(color), tree->extra_komi);
// assert(extra_komi >= 0);
floating_t orig_komi = extra_komi;
if (my_value < 0.5 && l->komi_ratchet > 0 && l->komi_ratchet != INFINITY) {
if (DEBUGL(0))
fprintf(stderr, "losing %f extra komi %.1f ratchet %.1f -> 0\n",
my_value, extra_komi, l->komi_ratchet);
/* Disable dynkomi completely, too dangerous in this game. */
extra_komi = l->komi_ratchet = 0;
} else if (my_value < l->orange_zone && extra_komi > 0) {
extra_komi = l->komi_ratchet = fmax(extra_komi - l->drop_step, 0.0);
if (extra_komi != orig_komi && DEBUGL(3))
fprintf(stderr, "dropping to %f, extra komi %.1f -> ratchet %.1f\n",
my_value, orig_komi, extra_komi);
} else if (my_value > l->green_zone && extra_komi + 1 <= l->komi_ratchet) {
extra_komi += 1;
if (extra_komi != orig_komi && DEBUGL(3))
fprintf(stderr, "winning %f extra_komi %.1f -> %.1f, ratchet %.1f\n",
my_value, orig_komi, extra_komi, l->komi_ratchet);
}
return komi_by_color(extra_komi, color);
}
static bool
test_moggy_moves(struct board *b, char *arg)
{
int runs = 1000;
coord_t *cc = str2coord(arg, board_size(b));
struct move last;
last.coord = *cc; coord_done(cc);
last.color = board_at(b, last.coord);
assert(last.color == S_BLACK || last.color == S_WHITE);
enum stone color = stone_other(last.color);
arg += strcspn(arg, " ") + 1;
b->last_move = last;
board_print(b, stderr); // Always print board so we see last move
char e_arg[128]; sprintf(e_arg, "runs=%i", runs);
struct engine *e = engine_replay_init(e_arg, b);
if (DEBUGL(1))
printf("moggy moves %s, %s to play. Sampling moves (%i runs)...\n\n",
coord2sstr(last.coord, b), stone2str(color), runs);
int played_[b->size2 + 2]; memset(played_, 0, sizeof(played_));
int *played = played_ + 2; // allow storing pass/resign
int most_played = 0;
replay_sample_moves(e, b, color, played, &most_played);
/* Show moves stats */
for (int k = most_played; k > 0; k--)
for (coord_t c = resign; c < b->size2; c++)
if (played[c] == k)
printf("%3s: %.2f%%\n", coord2str(c, b), (float)k * 100 / runs);
engine_done(e);
return true; // Not much of a unit test right now =)
}
int
uct_playout(struct uct *u, struct board *b, enum stone player_color, struct tree *t)
{
struct board b2;
board_copy(&b2, b);
struct playout_amafmap amaf;
amaf.gamelen = amaf.game_baselen = 0;
/* Walk the tree until we find a leaf, then expand it and do
* a random playout. */
struct tree_node *n = t->root;
enum stone node_color = stone_other(player_color);
assert(node_color == t->root_color);
/* Make sure the root node is expanded. */
if (tree_leaf_node(n) && !__sync_lock_test_and_set(&n->is_expanded, 1))
tree_expand_node(t, n, &b2, player_color, u, 1);
/* Tree descent history. */
/* XXX: This is somewhat messy since @n and descent[dlen-1].node are
* redundant. */
struct uct_descent descent[DESCENT_DLEN];
descent[0].node = n; descent[0].lnode = NULL;
int dlen = 1;
/* Total value of the sequence. */
struct move_stats seq_value = { .playouts = 0 };
/* The last "significant" node along the descent (i.e. node
* with higher than configured number of playouts). For black
* and white. */
struct tree_node *significant[2] = { NULL, NULL };
if (n->u.playouts >= u->significant_threshold)
significant[node_color - 1] = n;
int result;
int pass_limit = (board_size(&b2) - 2) * (board_size(&b2) - 2) / 2;
int passes = is_pass(b->last_move.coord) && b->moves > 0;
/* debug */
static char spaces[] = "\0 ";
/* /debug */
if (UDEBUGL(8))
fprintf(stderr, "--- UCT walk with color %d\n", player_color);
while (!tree_leaf_node(n) && passes < 2) {
spaces[dlen - 1] = ' '; spaces[dlen] = 0;
/*** Choose a node to descend to: */
/* Parity is chosen already according to the child color, since
* it is applied to children. */
node_color = stone_other(node_color);
int parity = (node_color == player_color ? 1 : -1);
assert(dlen < DESCENT_DLEN);
descent[dlen] = descent[dlen - 1];
if (u->local_tree && (!descent[dlen].lnode || descent[dlen].node->d >= u->tenuki_d)) {
/* Start new local sequence. */
/* Remember that node_color already holds color of the
* to-be-found child. */
descent[dlen].lnode = node_color == S_BLACK ? t->ltree_black : t->ltree_white;
}
if (!u->random_policy_chance || fast_random(u->random_policy_chance))
u->policy->descend(u->policy, t, &descent[dlen], parity, b2.moves > pass_limit);
else
u->random_policy->descend(u->random_policy, t, &descent[dlen], parity, b2.moves > pass_limit);
/*** Perform the descent: */
if (descent[dlen].node->u.playouts >= u->significant_threshold) {
significant[node_color - 1] = descent[dlen].node;
}
seq_value.playouts += descent[dlen].value.playouts;
seq_value.value += descent[dlen].value.value * descent[dlen].value.playouts;
n = descent[dlen++].node;
assert(n == t->root || n->parent);
if (UDEBUGL(7))
fprintf(stderr, "%s+-- UCT sent us to [%s:%d] %d,%f\n",
spaces, coord2sstr(node_coord(n), t->board),
node_coord(n), n->u.playouts,
tree_node_get_value(t, parity, n->u.value));
/* Add virtual loss if we need to; this is used to discourage
* other threads from visiting this node in case of multiple
* threads doing the tree search. */
if (u->virtual_loss)
stats_add_result(&n->u, node_color == S_BLACK ? 0.0 : 1.0, u->virtual_loss);
assert(node_coord(n) >= -1);
record_amaf_move(&amaf, node_coord(n));
struct move m = { node_coord(n), node_color };
int res = board_play(&b2, &m);
if (res < 0 || (!is_pass(m.coord) && !group_at(&b2, m.coord)) /* suicide */
|| b2.superko_violation) {
if (UDEBUGL(4)) {
for (struct tree_node *ni = n; ni; ni = ni->parent)
fprintf(stderr, "%s<%"PRIhash"> ", coord2sstr(node_coord(ni), t->board), ni->hash);
fprintf(stderr, "marking invalid %s node %d,%d res %d group %d spk %d\n",
stone2str(node_color), coord_x(node_coord(n),b), coord_y(node_coord(n),b),
res, group_at(&b2, m.coord), b2.superko_violation);
}
n->hints |= TREE_HINT_INVALID;
result = 0;
goto end;
}
if (is_pass(node_coord(n)))
passes++;
else
passes = 0;
enum stone next_color = stone_other(node_color);
/* We need to make sure only one thread expands the node. If
* we are unlucky enough for two threads to meet in the same
* node, the latter one will simply do another simulation from
* the node itself, no big deal. t->nodes_size may exceed
* the maximum in multi-threaded case but not by much so it's ok.
* The size test must be before the test&set not after, to allow
* expansion of the node later if enough nodes have been freed. */
if (tree_leaf_node(n)
&& n->u.playouts - u->virtual_loss >= u->expand_p && t->nodes_size < u->max_tree_size
&& !__sync_lock_test_and_set(&n->is_expanded, 1))
tree_expand_node(t, n, &b2, next_color, u, -parity);
}
amaf.game_baselen = amaf.gamelen;
if (t->use_extra_komi && u->dynkomi->persim) {
b2.komi += round(u->dynkomi->persim(u->dynkomi, &b2, t, n));
}
if (passes >= 2) {
/* XXX: No dead groups support. */
floating_t score = board_official_score(&b2, NULL);
/* Result from black's perspective (no matter who
* the player; black's perspective is always
* what the tree stores. */
result = - (score * 2);
if (UDEBUGL(5))
fprintf(stderr, "[%d..%d] %s p-p scoring playout result %d (W %f)\n",
player_color, node_color, coord2sstr(node_coord(n), t->board), result, score);
if (UDEBUGL(6))
board_print(&b2, stderr);
board_ownermap_fill(&u->ownermap, &b2);
} else { // assert(tree_leaf_node(n));
/* In case of parallel tree search, the assertion might
* not hold if two threads chew on the same node. */
result = uct_leaf_node(u, &b2, player_color, &amaf, descent, &dlen, significant, t, n, node_color, spaces);
}
if (u->policy->wants_amaf && u->playout_amaf_cutoff) {
unsigned int cutoff = amaf.game_baselen;
cutoff += (amaf.gamelen - amaf.game_baselen) * u->playout_amaf_cutoff / 100;
amaf.gamelen = cutoff;
}
/* Record the result. */
assert(n == t->root || n->parent);
floating_t rval = scale_value(u, b, result);
u->policy->update(u->policy, t, n, node_color, player_color, &amaf, &b2, rval);
if (t->use_extra_komi) {
stats_add_result(&u->dynkomi->score, result / 2, 1);
stats_add_result(&u->dynkomi->value, rval, 1);
}
if (u->local_tree && n->parent && !is_pass(node_coord(n)) && dlen > 0) {
/* Get the local sequences and record them in ltree. */
/* We will look for sequence starts in our descent
* history, then run record_local_sequence() for each
* found sequence start; record_local_sequence() may
* pick longer sequences from descent history then,
* which is expected as it will create new lnodes. */
enum stone seq_color = player_color;
/* First move always starts a sequence. */
record_local_sequence(u, t, &b2, descent, dlen, 1, seq_color);
seq_color = stone_other(seq_color);
for (int dseqi = 2; dseqi < dlen; dseqi++, seq_color = stone_other(seq_color)) {
if (u->local_tree_allseq) {
/* We are configured to record all subsequences. */
record_local_sequence(u, t, &b2, descent, dlen, dseqi, seq_color);
continue;
}
if (descent[dseqi].node->d >= u->tenuki_d) {
/* Tenuki! Record the fresh sequence. */
record_local_sequence(u, t, &b2, descent, dlen, dseqi, seq_color);
continue;
}
if (descent[dseqi].lnode && !descent[dseqi].lnode) {
/* Record result for in-descent picked sequence. */
record_local_sequence(u, t, &b2, descent, dlen, dseqi, seq_color);
continue;
}
}
}
end:
/* We need to undo the virtual loss we added during descend. */
if (u->virtual_loss) {
floating_t loss = node_color == S_BLACK ? 0.0 : 1.0;
for (; n->parent; n = n->parent) {
stats_rm_result(&n->u, loss, u->virtual_loss);
loss = 1.0 - loss;
}
}
board_done_noalloc(&b2);
return result;
}
int
uct_playouts(struct uct *u, struct board *b, enum stone color, struct tree *t, struct time_info *ti)
{
int i;
if (ti && ti->dim == TD_GAMES) {
for (i = 0; t->root->u.playouts <= ti->len.games && !uct_halt; i++)
uct_playout(u, b, color, t);
} else {
for (i = 0; !uct_halt; i++)
uct_playout(u, b, color, t);
}
return i;
}
static void
record_local_sequence(struct uct *u, struct tree *t, struct board *endb,
struct uct_descent *descent, int dlen, int di,
enum stone seq_color)
{
#define LTREE_DEBUG if (UDEBUGL(6))
/* Ignore pass sequences. */
if (is_pass(node_coord(descent[di].node)))
return;
LTREE_DEBUG board_print(endb, stderr);
LTREE_DEBUG fprintf(stderr, "recording local %s sequence: ",
stone2str(seq_color));
/* Sequences starting deeper are less relevant in general. */
int pval = LTREE_PLAYOUTS_MULTIPLIER;
if (u->local_tree && u->local_tree_depth_decay > 0)
pval = ((floating_t) pval) / pow(u->local_tree_depth_decay, di - 1);
if (!pval) {
LTREE_DEBUG fprintf(stderr, "too deep @%d\n", di);
return;
}
/* Pick the right local tree root... */
struct tree_node *lnode = seq_color == S_BLACK ? t->ltree_black : t->ltree_white;
lnode->u.playouts++;
double sval = 0.5;
if (u->local_tree_rootgoal) {
sval = local_value(u, endb, node_coord(descent[di].node), seq_color);
LTREE_DEBUG fprintf(stderr, "(goal %s[%s %1.3f][%d]) ",
coord2sstr(node_coord(descent[di].node), t->board),
stone2str(seq_color), sval, descent[di].node->d);
}
/* ...and record the sequence. */
int di0 = di;
while (di < dlen && (di == di0 || descent[di].node->d < u->tenuki_d)) {
enum stone color = (di - di0) % 2 ? stone_other(seq_color) : seq_color;
double rval;
if (u->local_tree_rootgoal)
rval = sval;
else
rval = local_value(u, endb, node_coord(descent[di].node), color);
LTREE_DEBUG fprintf(stderr, "%s[%s %1.3f][%d] ",
coord2sstr(node_coord(descent[di].node), t->board),
stone2str(color), rval, descent[di].node->d);
lnode = tree_get_node(t, lnode, node_coord(descent[di++].node), true);
assert(lnode);
stats_add_result(&lnode->u, rval, pval);
}
/* Add lnode for tenuki (pass) if we descended further. */
if (di < dlen) {
double rval = u->local_tree_rootgoal ? sval : 0.5;
LTREE_DEBUG fprintf(stderr, "pass ");
lnode = tree_get_node(t, lnode, pass, true);
assert(lnode);
stats_add_result(&lnode->u, rval, pval);
}
LTREE_DEBUG fprintf(stderr, "\n");
}
/* Syntax:
* moggy status (last_move) coord [coord...]
* Play number of random games starting from last_move
*
* moggy status coord [coord...]
* moggy status (b) coord [coord...]
* Black to play, pick random white last move
*
* moggy status (w) coord [coord...]
* White to play, pick random black last move
*/
static bool
test_moggy_status(struct board *board, char *arg)
{
int games = 4000;
coord_t status_at[10];
int n = 0;
enum stone color = S_BLACK;
int pick_random = true; // Pick random last move for each game
while (*arg && *arg != '#') {
if (*arg == ' ' || *arg == '\t') { arg++; continue; }
if (!strncmp(arg, "(b)", 3))
color = S_BLACK;
else if (!strncmp(arg, "(w)", 3))
color = S_WHITE;
else if (*arg == '(') { /* Optional "(last_move)" argument */
arg++; assert(isalpha(*arg));
pick_random = false;
struct move last;
last.coord = str2scoord(arg, board_size(board));
last.color = board_at(board, last.coord);
assert(last.color == S_BLACK || last.color == S_WHITE);
color = stone_other(last.color);
board->last_move = last;
}
else {
assert(isalpha(*arg));
status_at[n++] = str2scoord(arg, board_size(board));
}
arg += strcspn(arg, " \t");
}
board_print(board, stderr);
if (DEBUGL(1)) {
printf("moggy status ");
for (int i = 0; i < n; i++)
printf("%s%s", coord2sstr(status_at[i], board), (i != n-1 ? " " : ""));
printf(", %s to play. Playing %i games %s...\n",
stone2str(color), games, (pick_random ? "(random last move) " : ""));
}
struct playout_policy *policy = playout_moggy_init(NULL, board, NULL);
struct playout_setup setup = { .gamelen = MAX_GAMELEN };
struct board_ownermap ownermap;
ownermap.playouts = 0;
ownermap.map = malloc2(board_size2(board) * sizeof(ownermap.map[0]));
memset(ownermap.map, 0, board_size2(board) * sizeof(ownermap.map[0]));
/* Get final status estimate after a number of moggy games */
int wr = 0;
double time_start = time_now();
for (int i = 0; i < games; i++) {
struct board b;
board_copy(&b, board);
if (pick_random)
pick_random_last_move(&b, color);
int score = play_random_game(&setup, &b, color, NULL, &ownermap, policy);
if (color == S_WHITE)
score = -score;
wr += (score > 0);
board_done_noalloc(&b);
}
double elapsed = time_now() - time_start;
printf("moggy status in %.1fs, %i games/s\n\n", elapsed, (int)((float)games / elapsed));
int wr_black = wr * 100 / games;
int wr_white = (games - wr) * 100 / games;
if (wr_black > wr_white)
printf("Winrate: [ black %i%% ] white %i%%\n\n", wr_black, wr_white);
else
printf("Winrate: black %i%% [ white %i%% ]\n\n", wr_black, wr_white);
board_print_ownermap(board, stderr, &ownermap);
for (int i = 0; i < n; i++) {
coord_t c = status_at[i];
enum stone color = (ownermap.map[c][S_BLACK] > ownermap.map[c][S_WHITE] ? S_BLACK : S_WHITE);
fprintf(stderr, "%3s owned by %s: %i%%\n",
coord2sstr(c, board), stone2str(color),
ownermap.map[c][color] * 100 / ownermap.playouts);
}
free(ownermap.map);
playout_policy_done(policy);
return true; // Not much of a unit test right now =)
}
static void
board_load(struct board *b, FILE *f, unsigned int size)
{
board_printed = false;
board_resize(b, size);
board_clear(b);
for (int y = size - 1; y >= 0; y--) {
char line[256];
if (!fgets(line, sizeof(line), f)) {
fprintf(stderr, "Premature EOF.\n");
exit(EXIT_FAILURE);
}
line[strlen(line) - 1] = 0; // chomp
if (strlen(line) != size * 2 - 1) {
fprintf(stderr, "Line not %d char long: %s\n", size * 2 - 1, line);
exit(EXIT_FAILURE);
}
for (unsigned int i = 0; i < size * 2; i++) {
enum stone s;
switch (line[i]) {
case '.': s = S_NONE; break;
case 'X': s = S_BLACK; break;
case 'O': s = S_WHITE; break;
default: fprintf(stderr, "Invalid stone '%c'\n", line[i]);
exit(EXIT_FAILURE);
}
i++;
if (line[i] != ' ' && i/2 < size - 1) {
fprintf(stderr, "No space after stone %i: '%c'\n", i/2 + 1, line[i]);
exit(EXIT_FAILURE);
}
if (s == S_NONE) continue;
struct move m = { .color = s, .coord = coord_xy(b, i/2 + 1, y + 1) };
if (board_play(b, &m) < 0) {
fprintf(stderr, "Failed to play %s %s\n",
stone2str(s), coord2sstr(m.coord, b));
board_print(b, stderr);
exit(EXIT_FAILURE);
}
}
}
int suicides = b->captures[S_BLACK] || b->captures[S_WHITE];
assert(!suicides);
}
static void
set_ko(struct board *b, char *arg)
{
assert(isalpha(*arg));
struct move last;
last.coord = str2scoord(arg, board_size(b));
last.color = board_at(b, last.coord);
assert(last.color == S_BLACK || last.color == S_WHITE);
b->last_move = last;
/* Sanity checks */
group_t g = group_at(b, last.coord);
assert(board_group_info(b, g).libs == 1);
assert(group_stone_count(b, g, 2) == 1);
coord_t lib = board_group_info(b, g).lib[0];
assert(board_is_eyelike(b, lib, last.color));
b->ko.coord = lib;
b->ko.color = stone_other(last.color);
}