Upload policy_config.py with huggingface_hub

policy_config.py

@@ -10,7 +10,7 @@ exp_config = {
             'retry_waiting_time': 0.1,
             'cfg_type': 'BaseEnvManagerDict'
         },
-        'stop_value': 20,
+        'stop_value': 30,
         'n_evaluator_episode': 8,
         'env_id': 'PongNoFrameskip-v4',
         'collector_env_num': 8,
@@ -59,8 +59,9 @@ exp_config = {
                     'mode': 'train_iter'
                 },
                 'figure_path': None,
+                'return_env_info': True,
                 'cfg_type': 'InteractionSerialEvaluatorDict',
-                'stop_value': 20,
+                'stop_value': 30,
                 'n_episode': 8
             }
         },