zjowowen commited on
Commit
257a189
1 Parent(s): 9713690

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  type: PongNoFrameskip-v4
22
  metrics:
23
  - type: mean_reward
24
- value: 10.1 +/- 2.98
25
  name: mean_reward
26
  ---
27
 
@@ -149,7 +149,7 @@ pip3 install LightZero
149
  repo_id="OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero",
150
  platform_info="[LightZero](https://github.com/opendilab/LightZero) and [DI-engine](https://github.com/opendilab/di-engine)",
151
  model_description="**LightZero** is an efficient, easy-to-understand open-source toolkit that merges Monte Carlo Tree Search (MCTS) with Deep Reinforcement Learning (RL), simplifying their integration for developers and researchers. More details are in paper [LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios](https://huggingface.co/papers/2310.08348).",
152
- create_repo=True
153
  )
154
 
155
  ```
@@ -289,7 +289,7 @@ exp_config = {
289
  - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero/blob/main/replay.mp4)
290
  <!-- Provide the size information for the model. -->
291
  - **Parameters total size:** 33023.14 KB
292
- - **Last Update Date:** 2024-01-04
293
 
294
  ## Environments
295
  <!-- 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: PongNoFrameskip-v4
22
  metrics:
23
  - type: mean_reward
24
+ value: 5.8 +/- 4.92
25
  name: mean_reward
26
  ---
27
 
 
149
  repo_id="OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero",
150
  platform_info="[LightZero](https://github.com/opendilab/LightZero) and [DI-engine](https://github.com/opendilab/di-engine)",
151
  model_description="**LightZero** is an efficient, easy-to-understand open-source toolkit that merges Monte Carlo Tree Search (MCTS) with Deep Reinforcement Learning (RL), simplifying their integration for developers and researchers. More details are in paper [LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios](https://huggingface.co/papers/2310.08348).",
152
+ create_repo=False
153
  )
154
 
155
  ```
 
289
  - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-EfficientZero/blob/main/replay.mp4)
290
  <!-- Provide the size information for the model. -->
291
  - **Parameters total size:** 33023.14 KB
292
+ - **Last Update Date:** 2024-01-08
293
 
294
  ## Environments
295
  <!-- 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. -->