Push agent to the Hub

README.md

@@ -17,14 +17,14 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -154.37 +/- 121.32
+      value: -57.12 +/- 67.39
       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: -154.37 ± 121.32
+      - Mean Reward: -57.12 ± 67.39
       - 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.1750048361.2f208e49a865

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6e73f225229d95967ac77b3a824a1760c880a7c176fd3aa416d6c83264891e
+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": -154.37256569979098, "std_reward": 121.31941116407279, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:32:36.362091"}
+{"env_id": "LunarLander-v2", "mean_reward": -57.115931953417295, "std_reward": 67.39279984672822, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:33:33.891796"}