Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -147.20 +/- 39.12
+      value: -138.99 +/- 59.48
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 5000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1736525336.ed58eb65a230.4888.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234471ca1412cbd14c449eba937e81c1d1b0a28949690ccd32a1fbd3ceca7a8d
+size 11016

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e592fb92948eb720ebf65e9ba651a3ca7834e96ec574ac31ef975b4528652b8
-size 42898
+oid sha256:d96e60721876938ae0c2be595add1b957907e474c7dc945a016f12227868e3de
+size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -147.20454273276906, "std_reward": 39.119689752023845, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-10T14:35:28.773554"}
+{"env_id": "LunarLander-v2", "mean_reward": -138.99243939191302, "std_reward": 59.477818923145975, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-10T16:09:04.847482"}