Push agent to the Hub

README.md

@@ -17,14 +17,14 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -223.63 +/- 133.13
+      value: -134.63 +/- 62.92
       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: -223.63 ± 133.13
+      - Mean Reward: -134.63 ± 62.92
       - 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': 0.1
 'seed': 136
 'repo_id': 'proyrb/ppo-LunarLander-v2'
 'gae': True

logs/events.out.tfevents.1750047825.2f208e49a865

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c2cab4015e02a2421d24f3e679a810ce36915e536eb607eac874a9eb1af1c0
+size 433186

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d466f4852f3d65424844a9c82c43106d7fca7784014b68e98a14007c311fa3b
+oid sha256:4145d07a40fb7a03bfd8c6e015739c1088cf9086ec4b48c27273d664f417871f
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -223.6344459904147, "std_reward": 133.12613218024208, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:22:31.860447"}
+{"env_id": "LunarLander-v2", "mean_reward": -134.62835537496403, "std_reward": 62.9241868508749, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:24:34.762617"}