Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 205.60 +/- 113.19
+      value: -119.87 +/- 76.35
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing LunarLander-v2
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing LunarLander-v2.
     
   # Hyperparameters
   ```python
@@ -36,7 +36,7 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'CartPole-v1'
+'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4

logs/events.out.tfevents.1687635780.94df98923e00.64547.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a09ba0676e33d7d03bb3d117763da4dc62b09a198993f933abc23b11ba73a1
+size 110597

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f67f6ba66ae2b412b68822fb3e8969053f64353df4c555fddd526a057503c8b4
-size 39909
+oid sha256:73a6748cee3444894102db06ecc10eb21168fdd67939c4d5bf3a05379f763ac8
+size 42469

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 205.6, "std_reward": 113.18586484186088, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-24T19:41:53.336130"}
+{"env_id": "LunarLander-v2", "mean_reward": -119.86643162514659, "std_reward": 76.34551280690482, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-24T19:43:45.265177"}