Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- LunarLander-v3
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v3
-      type: LunarLander-v3
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -236.60 +/- 79.44
+      value: -219.16 +/- 119.83
       name: mean_reward
       verified: false
 ---
 
-    # PPO Agent Playing LunarLander-v3
+    # PPO Agent Playing LunarLander-v2
 
-    This is a trained model of a PPO agent playing LunarLander-v3.
+    This is a trained model of a PPO agent playing LunarLander-v2.
         
     # Hyperparameters
     ```python
@@ -36,7 +36,7 @@ track: False
 wandb_project_name: cleanRL
 wandb_entity: None
 capture_video: False
-env_id: LunarLander-v3
+env_id: LunarLander-v2
 total_timesteps: 5000
 learning_rate: 0.00025
 num_envs: 4

logs/events.out.tfevents.1755444784.DESKTOP-92SAKPB.3590.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e604256c8d494666e8e99ee54babd4295e0b61443b9d37f369a5dc54fd1e45
+size 10902

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2afe2ef2ab266f778ac78e7757cf603b67b6b37238227b185c3cc82738fa84
+oid sha256:4f69d10d7e75e8051f99a395721aa99c59e6b18c1544f13e6901cdfdfb4e00b5
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v3", "mean_reward": -236.60097099794766, "std_reward": 79.44096628543107, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-17T18:28:25.656580"}
+{"env_id": "LunarLander-v2", "mean_reward": -219.15576941993976, "std_reward": 119.82658505566214, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-17T18:33:14.272316"}