Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -180.89 +/- 68.57
+      value: -104.01 +/- 37.02
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1741968147.KASHYYYK.10564.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec3415f835379c1c98940e7b2df8a10b3b8257a9ee3b5e80816e7752efff40e0
+size 221337

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d45f41ffaed07698efbbc11f016982ca72e9a87eff01495dc43653d74a1ecdb
+oid sha256:82139e6c36eb8ca252be9762245bc12f8d078c989172acf9ed7a156bd3b39689
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -180.8862565938803, "std_reward": 68.56731043083896, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-14T16:54:39.200289"}
+{"env_id": "LunarLander-v2", "mean_reward": -104.00537564700994, "std_reward": 37.01800309301719, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-14T17:03:42.091634"}