Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.66 +/- 70.30
+      value: -129.92 +/- 116.14
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.0008
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1745975522.59b34e00c18a.6386.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda3b16146b13491fac4d7cf404ce60e221903261cc480715c79ac0a0a67055f
+size 111957

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31dae05d29475ad69cdf82b58c3d030d8cec5d1f808c24d976d89cc1e770b11c
+oid sha256:c6ab10336dc8f76e665d7a0c41003cca643e84473180835609fe0917b7f9ca0c
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -150.65650590903107, "std_reward": 70.3014696369305, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-30T01:10:59.488354"}
+{"env_id": "LunarLander-v2", "mean_reward": -129.92128030534388, "std_reward": 116.13534953481015, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-30T01:12:39.625744"}