Push Reinforce agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- LunarLander-v2
+- CartPole-v1
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -11,19 +11,19 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -112.60 +/- 107.42
+      value: 166.00 +/- 55.22
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
+      name: CartPole-v1
+      type: CartPole-v1
 ---
 
-  # PPO Agent Playing LunarLander-v2
+  # PPO Agent Playing CartPole-v1
 
-  This is a trained model of a PPO agent playing LunarLander-v2.
+  This is a trained model of a PPO agent playing CartPole-v1.
   To learn to code your own PPO agent and train it Unit 8 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit8
   
   # Hyperparameters
@@ -36,7 +36,7 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'LunarLander-v2'
+'env_id': 'CartPole-v1'
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4

logs/events.out.tfevents.1662590309.nt-pc.11485.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327003697481a51f2d0682c8b8d4ceebac7f2a6551b2c4e8cf737f81255011a9
+size 116432

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda0e6fa965668f39fdf95e4f2deb1cafd6cf6c90bf65a20693583a68d3d98e7
-size 42689
+oid sha256:615063e1c901e83f6483e95e25739786a9c37a58a7e03e55a1c56f95f7e1493a
+size 40129

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -112.6023172789165, "std_reward": 107.4201506784575, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-08T05:25:35.416844"}
+{"env_id": "CartPole-v1", "mean_reward": 166.0, "std_reward": 55.22499434133063, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-08T05:38:57.571085"}