zjowowen commited on
Commit
0ad182c
1 Parent(s): 080a39c

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: BreakoutNoFrameskip-v4
22
  metrics:
23
  - type: mean_reward
24
- value: 2.4 +/- 3.04
25
  name: mean_reward
26
  ---
27
 
@@ -149,7 +149,7 @@ pip3 install LightZero
149
  repo_id="OpenDILabCommunity/PongNoFrameskip-v4-MuZero",
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
  ```
@@ -290,7 +290,7 @@ exp_config = {
290
  - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/BreakoutNoFrameskip-v4-MuZero/blob/main/replay.mp4)
291
  <!-- Provide the size information for the model. -->
292
  - **Parameters total size:** 24008.38 KB
293
- - **Last Update Date:** 2023-12-16
294
 
295
  ## Environments
296
  <!-- 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: BreakoutNoFrameskip-v4
22
  metrics:
23
  - type: mean_reward
24
+ value: 6.6 +/- 3.58
25
  name: mean_reward
26
  ---
27
 
 
149
  repo_id="OpenDILabCommunity/PongNoFrameskip-v4-MuZero",
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
  ```
 
290
  - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/BreakoutNoFrameskip-v4-MuZero/blob/main/replay.mp4)
291
  <!-- Provide the size information for the model. -->
292
  - **Parameters total size:** 24008.38 KB
293
+ - **Last Update Date:** 2023-12-20
294
 
295
  ## Environments
296
  <!-- 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. -->