Upload policy_config.py with huggingface_hub
Browse files- policy_config.py +5 -4
policy_config.py
CHANGED
|
@@ -10,11 +10,11 @@ exp_config = {
|
|
| 10 |
'retry_waiting_time': 0.1,
|
| 11 |
'cfg_type': 'BaseEnvManagerDict'
|
| 12 |
},
|
| 13 |
-
'stop_value':
|
|
|
|
| 14 |
'env_id': 'LunarLanderContinuous-v2',
|
| 15 |
'collector_env_num': 8,
|
| 16 |
'evaluator_env_num': 8,
|
| 17 |
-
'n_evaluator_episode': 8,
|
| 18 |
'act_scale': True
|
| 19 |
},
|
| 20 |
'policy': {
|
|
@@ -69,9 +69,10 @@ exp_config = {
|
|
| 69 |
'render_freq': -1,
|
| 70 |
'mode': 'train_iter'
|
| 71 |
},
|
|
|
|
| 72 |
'cfg_type': 'InteractionSerialEvaluatorDict',
|
| 73 |
-
'
|
| 74 |
-
'
|
| 75 |
}
|
| 76 |
},
|
| 77 |
'other': {
|
|
|
|
| 10 |
'retry_waiting_time': 0.1,
|
| 11 |
'cfg_type': 'BaseEnvManagerDict'
|
| 12 |
},
|
| 13 |
+
'stop_value': 260,
|
| 14 |
+
'n_evaluator_episode': 8,
|
| 15 |
'env_id': 'LunarLanderContinuous-v2',
|
| 16 |
'collector_env_num': 8,
|
| 17 |
'evaluator_env_num': 8,
|
|
|
|
| 18 |
'act_scale': True
|
| 19 |
},
|
| 20 |
'policy': {
|
|
|
|
| 69 |
'render_freq': -1,
|
| 70 |
'mode': 'train_iter'
|
| 71 |
},
|
| 72 |
+
'figure_path': None,
|
| 73 |
'cfg_type': 'InteractionSerialEvaluatorDict',
|
| 74 |
+
'stop_value': 260,
|
| 75 |
+
'n_episode': 8
|
| 76 |
}
|
| 77 |
},
|
| 78 |
'other': {
|