Fix 2048 spawn count and add 16384 stat

pufferlib/ocean/g2048/binding.h

@@ -21,6 +21,7 @@ void my_log(Log* log, Dict* out) {
     dict_set(out, "episode_return", log->episode_return);
     dict_set(out, "episode_length", log->episode_length);
     dict_set(out, "lifetime_max_tile", log->lifetime_max_tile);
+    dict_set(out, "reached_16384", log->reached_16384);
     dict_set(out, "reached_32768", log->reached_32768);
     dict_set(out, "reached_65536", log->reached_65536);
     dict_set(out, "reached_131072", log->reached_131072);

pufferlib/ocean/g2048/eval.py

@@ -29,6 +29,7 @@ def evaluate(env_name, load_model_path):
     episode_lengths = sum(n * l for n, l in zip(stats['n'], stats['episode_length'])) / num_episodes
     max_tiles = sum(n * m for n, m in zip(stats['n'], stats['score'])) / num_episodes
     merge_scores = sum(n * s for n, s in zip(stats['n'], stats['merge_score'])) / num_episodes
+    reached_16384 = sum(n * s for n, s in zip(stats['n'], stats['reached_16384'])) / num_episodes
     reached_32768 = sum(n * s for n, s in zip(stats['n'], stats['reached_32768'])) / num_episodes
     reached_65536 = sum(n * s for n, s in zip(stats['n'], stats['reached_65536'])) / num_episodes
     reached_131072 = sum(n * s for n, s in zip(stats['n'], stats['reached_131072'])) / num_episodes
@@ -38,6 +39,7 @@ def evaluate(env_name, load_model_path):
     # The stats from vecenv are averaged across envs that were done in the same tick. Cannot get the single max.
     print(f"Episode length -- Avg: {episode_lengths:.1f}, Max: {max(stats['episode_length']):.1f}")
     print(f"Merge score -- Avg: {merge_scores:.1f}, Max: {max(stats['merge_score']):.1f}")
+    print(f"Reached 16384 prob: {reached_16384*100:.2f} %")
     print(f"Reached 32768 prob: {reached_32768*100:.2f} %")
     print(f"Reached 65536 prob: {reached_65536*100:.2f} %")
     print(f"Reached 131072 prob: {reached_131072*100:.2f} %")

pufferlib/ocean/g2048/g2048.h

@@ -39,15 +39,16 @@ static inline float calculate_perf(unsigned char max_tile) {
 typedef struct Log {
     float perf;
     float score;
-    float merge_score;
-    float episode_return;
-    float episode_length;
-    float lifetime_max_tile;
-    float reached_32768;
-    float reached_65536;
-    float reached_131072;
-    float n;
-} Log;
+    float merge_score;
+    float episode_return;
+    float episode_length;
+    float lifetime_max_tile;
+    float reached_16384;
+    float reached_32768;
+    float reached_65536;
+    float reached_131072;
+    float n;
+} Log;
 
 typedef struct Game {
     Log log;                        // Required
@@ -130,13 +131,14 @@ void add_log(Game* game) {
 
     game->log.score += (float)(1 << game->max_tile);
     game->log.perf += calculate_perf(game->max_tile);
-    game->log.merge_score += (float)game->score;
-    game->log.episode_length += game->tick;
-    game->log.episode_return += game->episode_reward;
-    game->log.lifetime_max_tile += (float)(1 << game->lifetime_max_tile);
-    game->log.reached_32768 += (game->max_tile >= 15);
-    game->log.reached_65536 += (game->max_tile >= 16);
-    game->log.reached_131072 += (game->max_tile >= 17);
+    game->log.merge_score += (float)game->score;
+    game->log.episode_length += game->tick;
+    game->log.episode_return += game->episode_reward;
+    game->log.lifetime_max_tile += (float)(1 << game->lifetime_max_tile);
+    game->log.reached_16384 += (game->max_tile >= 14);
+    game->log.reached_32768 += (game->max_tile >= 15);
+    game->log.reached_65536 += (game->max_tile >= 16);
+    game->log.reached_131072 += (game->max_tile >= 17);
     game->log.n += 1;
 }
 
@@ -368,12 +370,12 @@ void c_step(Game* game) {
     bool did_move = move(game, game->actions[0] + 1, &reward, &score_add);
     game->tick++;
 
-    if (did_move) {
-        game->moves_made++;
-        place_tile_at_random_cell(game, get_new_tile());
-        game->score += score_add;
-
-        update_stats(game);
+    if (did_move) {
+        game->moves_made++;
+        // Refresh empty_count after merges so spawning uses the correct count.
+        update_stats(game);
+        place_tile_at_random_cell(game, get_new_tile());
+        game->score += score_add;
 
         // Observations only change if the grid changes
         update_observations(game);
@@ -413,11 +415,12 @@ void step_without_reset(Game* game) {
     bool did_move = move(game, game->actions[0] + 1, &reward, &score_add);
     game->tick++;
 
-    if (did_move) {
-        game->moves_made++;
-        place_tile_at_random_cell(game, get_new_tile());
-        game->score += score_add;
-        update_stats(game);
+    if (did_move) {
+        game->moves_made++;
+        // Refresh empty_count after merges so spawning uses the correct count.
+        update_stats(game);
+        place_tile_at_random_cell(game, get_new_tile());
+        game->score += score_add;
         // Observations only change if the grid changes
         update_observations(game);
     }