Push agent to the Hub

README.md

@@ -17,14 +17,14 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -124.86 +/- 96.75
+      value: -56.14 +/- 76.83
       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: -124.86 ± 96.75
+      - Mean Reward: -56.14 ± 76.83
       - Number of Evaluation Episodes: 10
       ## Hyperparameters
       ```python
@@ -35,7 +35,7 @@ model-index:
 'num_steps': 2048
 'update_epochs': 10
 'num_minibatches': 32
-'clip_coef': 0.4
+'clip_coef': 0.5
 'seed': 136
 'repo_id': 'proyrb/ppo-LunarLander-v2'
 'gae': True

logs/events.out.tfevents.1750048483.2f208e49a865

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cafead88bbcef6f7c7b7e9577f40eb5ea45041a53dafdc97e218f48a8f6aa0dc
+size 433186

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcdfed90f1e106194101277e862364cfcffdf9c8db73c59d8bbc1d70a5e7c034
+oid sha256:711f631489744c76c1b523bbd9f1aa0e316f76aa91bdc81baf07762208439429
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -124.85725039072898, "std_reward": 96.74626833983247, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:34:39.310874"}
+{"env_id": "LunarLander-v2", "mean_reward": -56.1384002722621, "std_reward": 76.8259730992556, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:35:43.242088"}