Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
type: OpenAI/Gym/Atari-PongNoFrameskip-v4
|
22 |
metrics:
|
23 |
- type: mean_reward
|
24 |
-
value:
|
25 |
name: mean_reward
|
26 |
---
|
27 |
|
@@ -219,7 +219,6 @@ exp_config = {
|
|
219 |
'mode': 'train_iter'
|
220 |
},
|
221 |
'figure_path': None,
|
222 |
-
'return_env_info': True,
|
223 |
'cfg_type': 'InteractionSerialEvaluatorDict',
|
224 |
'stop_value': 30,
|
225 |
'n_episode': 8
|
@@ -274,13 +273,13 @@ exp_config = {
|
|
274 |
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-C51/blob/main/replay.mp4)
|
275 |
<!-- Provide the size information for the model. -->
|
276 |
- **Parameters total size:** 55276.2 KB
|
277 |
-
- **Last Update Date:** 2023-
|
278 |
|
279 |
## Environments
|
280 |
<!-- 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. -->
|
281 |
- **Benchmark:** OpenAI/Gym/Atari
|
282 |
- **Task:** PongNoFrameskip-v4
|
283 |
- **Gym version:** 0.25.1
|
284 |
-
- **DI-engine version:** v0.4.
|
285 |
- **PyTorch version:** 2.0.1+cu117
|
286 |
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html)
|
|
|
21 |
type: OpenAI/Gym/Atari-PongNoFrameskip-v4
|
22 |
metrics:
|
23 |
- type: mean_reward
|
24 |
+
value: 20.3 +/- 0.64
|
25 |
name: mean_reward
|
26 |
---
|
27 |
|
|
|
219 |
'mode': 'train_iter'
|
220 |
},
|
221 |
'figure_path': None,
|
|
|
222 |
'cfg_type': 'InteractionSerialEvaluatorDict',
|
223 |
'stop_value': 30,
|
224 |
'n_episode': 8
|
|
|
273 |
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-C51/blob/main/replay.mp4)
|
274 |
<!-- Provide the size information for the model. -->
|
275 |
- **Parameters total size:** 55276.2 KB
|
276 |
+
- **Last Update Date:** 2023-09-21
|
277 |
|
278 |
## Environments
|
279 |
<!-- 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. -->
|
280 |
- **Benchmark:** OpenAI/Gym/Atari
|
281 |
- **Task:** PongNoFrameskip-v4
|
282 |
- **Gym version:** 0.25.1
|
283 |
+
- **DI-engine version:** v0.4.9
|
284 |
- **PyTorch version:** 2.0.1+cu117
|
285 |
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html)
|