Upload README.md with huggingface_hub

README.md

@@ -2,9 +2,11 @@
 library_name: stable-baselines3
 tags:
 - PandaReachDense-v3
-- deep-reinforcement-learning
 - reinforcement-learning
 - stable-baselines3
+- a2c
+- deep-rl
+- panda-gym
 model-index:
 - name: A2C
   results:
@@ -16,22 +18,52 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.25 +/- 0.15
+      value: 0.00 +/- 0.00 # 请根据你之前的 print 结果修改这里
       name: mean_reward
-      verified: false
 ---
 
-# **A2C** Agent playing **PandaReachDense-v3**
-This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+# A2C Agent playing PandaReachDense-v3
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+This is a trained model of an **A2C** agent playing **PandaReachDense-v3** using the [stable-baselines3](https://github.com/DLR-RM/stable-baselines3) library and the [panda-gym](https://github.com/qgallouedec/panda-gym) environment.
 
+## Video Replay
+
+![Replay Video](replay.mp4)
+
+## Usage (with huggingface_sb3)
+
+To use this model, you need to install the following dependencies:
+
+```python
+pip install stable-baselines3 huggingface_sb3 panda_gym shimmy
+
+Then you can load and evaluate the model:
 
 ```python
-from stable_baselines3 import ...
 from huggingface_sb3 import load_from_hub
+from stable_baselines3 import A2C
+from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
+
+# Load the model and statistics
+repo_id = "LuckLin/a2c-PandaReachDense-v3"
+filename = "a2c-PandaReachDense-v3.zip"
+
+checkpoint = load_from_hub(repo_id, filename)
+model = A2C.load(checkpoint)
+
+# Load the normalization statistics
+stats_path = load_from_hub(repo_id, "vec_normalize.pkl")
+env = DummyVecEnv([lambda: gym.make("PandaReachDense-v3")])
+env = VecNormalize.load(stats_path, env)
+
+# At test time, we don't update the stats
+env.training = False
+env.norm_reward = False
+
+# Evaluate
+obs = env.reset()
+for _ in range(1000):
+    action, _states = model.predict(obs, deterministic=True)
+    obs, rewards, dones, info = env.step(action)
+    env.render()
 
-...
-```