Push agent to the Hub

README.md

@@ -17,14 +17,14 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -92.71 +/- 79.03
+      value: -169.80 +/- 105.50
       name: mean_reward
       verified: false
 ---
 # PPO Agent Playing LunarLander-v2
       This is a trained model of a PPO agent playing LunarLander-v2.
       ## Evaluation Results
-      - Mean Reward: -92.71 ± 79.03
+      - Mean Reward: -169.80 ± 105.50
       - Number of Evaluation Episodes: 10
       ## Hyperparameters
       ```python
@@ -35,7 +35,7 @@ model-index:
 'num_steps': 2048
 'update_epochs': 10
 'num_minibatches': 32
-'clip_coef': 0.2
+'clip_coef': 0.3
 'seed': 136
 'repo_id': 'proyrb/ppo-LunarLander-v2'
 'gae': True

logs/events.out.tfevents.1750048156.2f208e49a865

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d1d3b178d7a97bf0c092e1ea7e4f41bfad4d2aad6dbd9a7ef6ed67ebf015d9
+size 433186

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d466f4852f3d65424844a9c82c43106d7fca7784014b68e98a14007c311fa3b
+oid sha256:b93c96427e4954cbd5a5657d5977b4436a9be477cd0e3a348500bb9def5059a8
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -92.70867756340857, "std_reward": 79.027337238784, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:29:12.011621"}
+{"env_id": "LunarLander-v2", "mean_reward": -169.8021350882041, "std_reward": 105.49741203393872, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:30:09.026469"}