Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: CartPole-v0
     metrics:
     - type: mean_reward
-      value: 146.4 +/- 5.33
+      value: 194.3 +/- 7.42
       name: mean_reward
 ---
 
@@ -29,11 +29,11 @@ model-index:
 
 ## Model Description
 <!-- Provide a longer summary of what this model is. -->
-This is a simple **MuZero** implementation to OpenAI/Gym/Box2d **CartPole-v0** by using [DI-engine](https://github.com/opendilab/di-engine) and [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
+This is a simple **MuZero** implementation to OpenAI/Gym/Box2d **CartPole-v0** by using [DI-engine](https://github.com/opendilab/di-engine) and [LightZero](https://github.com/opendilab/LightZero).
 
 **DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported  by reusing different abstraction levels of DI-engine reinforcement learning framework.
 
-
+**LightZero** is a lightweight, efficient, and easy-to-understand open-source algorithm toolkit that combines Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (RL).
 
 ## Model Usage
 ### Install the Dependencies
@@ -142,6 +142,8 @@ push_model_to_hub(
     usage_file_by_huggingface_ding="./muzero/cartpole_muzero_download.py",
     train_file="./muzero/cartpole_muzero.py",
     repo_id="OpenDILabCommunity/CartPole-v0-MuZero",
+    platform_info="[DI-engine](https://github.com/opendilab/di-engine) and [LightZero](https://github.com/opendilab/LightZero)",
+    model_description="**LightZero** is a lightweight, efficient, and easy-to-understand open-source algorithm toolkit that combines Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (RL).",
     create_repo=False
 )