Handle numpy types in monitor

Fixes openai#452

gym/monitoring/monitor_manager.py

@@ -180,7 +180,7 @@ def _flush(self, force=False):
                 'videos': [(os.path.basename(v), os.path.basename(m))
                            for v, m in self.videos],
                 'env_info': self._env_info(),
-            }, f)
+            }, f, default=json_encode)
 
     def close(self):
         """Flush all monitor data to disk and close any open rending windows."""
@@ -408,3 +408,21 @@ def collapse_env_infos(env_infos, training_dir):
         if key not in first:
             raise error.Error("env_info {} from training directory {} is missing expected key {}. This is unexpected and likely indicates a bug in gym.".format(first, training_dir, key))
     return first
+
+
+def json_encode(obj):
+    """
+    JSON can't serialize numpy types, so convert to pure python
+    """
+    if isinstance(obj, np.ndarray):
+        return list(obj)
+    elif isinstance(obj, np.float32):
+        return float(obj)
+    elif isinstance(obj, np.float64):
+        return float(obj)
+    elif isinstance(obj, np.int32):
+        return int(obj)
+    elif isinstance(obj, np.int64):
+        return int(obj)
+    else:
+        return obj

gym/monitoring/stats_recorder.py

@@ -81,7 +81,7 @@ def after_reset(self, observation):
     def save_complete(self):
         if self.steps is not None:
             self.episode_lengths.append(self.steps)
-            self.episode_rewards.append(self.rewards)
+            self.episode_rewards.append(float(self.rewards))
             self.timestamps.append(time.time())
 
     def close(self):