Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -138.79 +/- 38.57
+      value: -128.13 +/- 74.81
       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': 150000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1756317601.pdemu1cml000287.305248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be30b0f2fadaff0224aa65eb1c06e0e36a386d208b13a96870e3080bf6e1a47
+size 312819

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499762341ac0341409d47eb811da8269bb0fb329cefb732d708d6b88120e7c9b
+oid sha256:9a5b67b6f054cacc5ceb71b253293f26ac6c1021b673ebfdd0867b70e5fd4569
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -138.78647700877724, "std_reward": 38.56891026066861, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-27T19:57:10.211995"}
+{"env_id": "LunarLander-v2", "mean_reward": -128.13280423858535, "std_reward": 74.8068391844471, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-27T20:00:58.452526"}