Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: -157.75 +/- 101.56
+      value: -158.20 +/- 83.91
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v3'
-'total_timesteps': 50000
+'total_timesteps': 10000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1751219358.a24f5978913f.21327.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c89909e102f0e808f1ec57174eff7e9260cdb675de93d4942c73bc3c2245bf
+size 10341

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e492b6a62bfde66ff21004e13d7ddca01e590c225487735c1e6d6992a87f98
+oid sha256:028ecfb0f2264693e729f742d292c83d21d6953050c4644c061d5b9c86d546b7
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v3", "mean_reward": -157.75189377816855, "std_reward": 101.56336095985446, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-29T17:22:09.536962"}
+{"env_id": "LunarLander-v3", "mean_reward": -158.2010216390989, "std_reward": 83.91409759428667, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-29T17:50:16.133802"}