Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -104.01 +/- 37.02
+      value: 45.49 +/- 133.82
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 2000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1741968304.KASHYYYK.11046.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7abd76438a637c9d6bd632966fd5617a3716955b3e750bfeab1f3f0fff9c6eb
+size 2606437

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82139e6c36eb8ca252be9762245bc12f8d078c989172acf9ed7a156bd3b39689
+oid sha256:8bd8b64389873260902a33a38c5fd92319768d8b86c37ec33b7c9a700f3acd39
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -104.00537564700994, "std_reward": 37.01800309301719, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-14T17:03:42.091634"}
+{"env_id": "LunarLander-v2", "mean_reward": 45.48699046246717, "std_reward": 133.82123906001766, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-14T17:38:46.616604"}