Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 104.86 +/- 67.1
+      value: 163.44 +/- 97.96
       name: mean_reward
 ---
 
@@ -129,7 +129,7 @@ from huggingface_ding import push_model_to_hub
 # Instantiate the agent
 agent = EfficientZeroAgent(env_id="LunarLander-v2", exp_name="LunarLander-v2-EfficientZero")
 # Train the agent
-return_ = agent.train(step=int(5000000))
+return_ = agent.train(step=int(20000000))
 # Push model to huggingface hub
 push_model_to_hub(
     agent=agent.best,
@@ -149,7 +149,7 @@ pip3 install LightZero
     repo_id="OpenDILabCommunity/LunarLander-v2-EfficientZero",
     platform_info="[LightZero](https://github.com/opendilab/LightZero) and [DI-engine](https://github.com/opendilab/di-engine)",
     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).",
-    create_repo=True
+    create_repo=False
 )
 
 ```
@@ -291,7 +291,7 @@ exp_config = {
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-EfficientZero/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 17535.39 KB
-- **Last Update Date:** 2024-01-09
+- **Last Update Date:** 2024-01-17
 
 ## Environments
 <!-- 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. -->