Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- LunarLander-v2
+- CartPole-v1
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
+      name: CartPole-v1
+      type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: -209.95 +/- 113.92
+      value: 19.20 +/- 7.72
       name: mean_reward
       verified: false
 ---
 
-  # 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.
 
   # Hyperparameters
   ```python
@@ -36,8 +36,8 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'LunarLander-v2'
-'total_timesteps': 50
+'env_id': 'CartPole-v1'
+'total_timesteps': 500
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1682423855.B-Q6RGMD6R-0633.local.12779.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c4e83de4d6d2e445e2bde90cf24004c636127d8caee5ec54434f64ee70c6dd6
+size 676

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5a455d1425ae0765cfb4abe259248ae62df6b706958f5784d74743a759fbf5
-size 42469
+oid sha256:634ab1d5ddd947c681b3d718cd6078a561170e02ee6e851283178c72a13737a2
+size 39909

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -209.95315987153458, "std_reward": 113.91734962003916, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-25T19:33:28.271333"}
+{"env_id": "CartPole-v1", "mean_reward": 19.2, "std_reward": 7.717512552629895, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-25T19:57:36.723038"}