Upload policy_config.py with huggingface_hub
Browse files- policy_config.py +6 -5
policy_config.py
CHANGED
|
@@ -11,10 +11,10 @@ exp_config = {
|
|
| 11 |
'cfg_type': 'BaseEnvManagerDict'
|
| 12 |
},
|
| 13 |
'stop_value': 200,
|
|
|
|
| 14 |
'collector_env_num': 8,
|
| 15 |
'evaluator_env_num': 8,
|
| 16 |
-
'env_id': 'LunarLander-v2'
|
| 17 |
-
'n_evaluator_episode': 8
|
| 18 |
},
|
| 19 |
'policy': {
|
| 20 |
'model': {
|
|
@@ -59,9 +59,10 @@ exp_config = {
|
|
| 59 |
'render_freq': -1,
|
| 60 |
'mode': 'train_iter'
|
| 61 |
},
|
|
|
|
| 62 |
'cfg_type': 'InteractionSerialEvaluatorDict',
|
| 63 |
-
'
|
| 64 |
-
'
|
| 65 |
}
|
| 66 |
},
|
| 67 |
'other': {
|
|
@@ -87,7 +88,7 @@ exp_config = {
|
|
| 87 |
'nstep': 3,
|
| 88 |
'cfg_type': 'C51PolicyDict'
|
| 89 |
},
|
| 90 |
-
'exp_name': '
|
| 91 |
'seed': 0,
|
| 92 |
'wandb_logger': {
|
| 93 |
'gradient_logger': True,
|
|
|
|
| 11 |
'cfg_type': 'BaseEnvManagerDict'
|
| 12 |
},
|
| 13 |
'stop_value': 200,
|
| 14 |
+
'n_evaluator_episode': 8,
|
| 15 |
'collector_env_num': 8,
|
| 16 |
'evaluator_env_num': 8,
|
| 17 |
+
'env_id': 'LunarLander-v2'
|
|
|
|
| 18 |
},
|
| 19 |
'policy': {
|
| 20 |
'model': {
|
|
|
|
| 59 |
'render_freq': -1,
|
| 60 |
'mode': 'train_iter'
|
| 61 |
},
|
| 62 |
+
'figure_path': None,
|
| 63 |
'cfg_type': 'InteractionSerialEvaluatorDict',
|
| 64 |
+
'stop_value': 200,
|
| 65 |
+
'n_episode': 8
|
| 66 |
}
|
| 67 |
},
|
| 68 |
'other': {
|
|
|
|
| 88 |
'nstep': 3,
|
| 89 |
'cfg_type': 'C51PolicyDict'
|
| 90 |
},
|
| 91 |
+
'exp_name': 'LunarLander-v2-C51',
|
| 92 |
'seed': 0,
|
| 93 |
'wandb_logger': {
|
| 94 |
'gradient_logger': True,
|