Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ model-index:
|
|
| 21 |
type: OpenAI/Gym/Box2d-LunarLander-v2
|
| 22 |
metrics:
|
| 23 |
- type: mean_reward
|
| 24 |
-
value:
|
| 25 |
name: mean_reward
|
| 26 |
---
|
| 27 |
|
|
@@ -114,7 +114,7 @@ exp_config = {
|
|
| 114 |
'retry_waiting_time': 0.1,
|
| 115 |
'cfg_type': 'BaseEnvManagerDict'
|
| 116 |
},
|
| 117 |
-
'stop_value':
|
| 118 |
'n_evaluator_episode': 8,
|
| 119 |
'collector_env_num': 8,
|
| 120 |
'evaluator_env_num': 8,
|
|
@@ -164,8 +164,9 @@ exp_config = {
|
|
| 164 |
'mode': 'train_iter'
|
| 165 |
},
|
| 166 |
'figure_path': None,
|
|
|
|
| 167 |
'cfg_type': 'InteractionSerialEvaluatorDict',
|
| 168 |
-
'stop_value':
|
| 169 |
'n_episode': 8
|
| 170 |
}
|
| 171 |
},
|
|
@@ -208,7 +209,7 @@ exp_config = {
|
|
| 208 |
|
| 209 |
**Training Procedure**
|
| 210 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 211 |
-
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/
|
| 212 |
|
| 213 |
## Model Information
|
| 214 |
<!-- Provide the basic links for the model. -->
|
|
@@ -218,7 +219,7 @@ exp_config = {
|
|
| 218 |
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-C51/blob/main/replay.mp4)
|
| 219 |
<!-- Provide the size information for the model. -->
|
| 220 |
- **Parameters total size:** 214.3 KB
|
| 221 |
-
- **Last Update Date:** 2023-
|
| 222 |
|
| 223 |
## Environments
|
| 224 |
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
|
|
|
|
| 21 |
type: OpenAI/Gym/Box2d-LunarLander-v2
|
| 22 |
metrics:
|
| 23 |
- type: mean_reward
|
| 24 |
+
value: 196.19 +/- 78.51
|
| 25 |
name: mean_reward
|
| 26 |
---
|
| 27 |
|
|
|
|
| 114 |
'retry_waiting_time': 0.1,
|
| 115 |
'cfg_type': 'BaseEnvManagerDict'
|
| 116 |
},
|
| 117 |
+
'stop_value': 260,
|
| 118 |
'n_evaluator_episode': 8,
|
| 119 |
'collector_env_num': 8,
|
| 120 |
'evaluator_env_num': 8,
|
|
|
|
| 164 |
'mode': 'train_iter'
|
| 165 |
},
|
| 166 |
'figure_path': None,
|
| 167 |
+
'return_env_info': True,
|
| 168 |
'cfg_type': 'InteractionSerialEvaluatorDict',
|
| 169 |
+
'stop_value': 260,
|
| 170 |
'n_episode': 8
|
| 171 |
}
|
| 172 |
},
|
|
|
|
| 209 |
|
| 210 |
**Training Procedure**
|
| 211 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 212 |
+
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/Lunarlander-v2-C51)
|
| 213 |
|
| 214 |
## Model Information
|
| 215 |
<!-- Provide the basic links for the model. -->
|
|
|
|
| 219 |
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-C51/blob/main/replay.mp4)
|
| 220 |
<!-- Provide the size information for the model. -->
|
| 221 |
- **Parameters total size:** 214.3 KB
|
| 222 |
+
- **Last Update Date:** 2023-08-03
|
| 223 |
|
| 224 |
## Environments
|
| 225 |
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
|