Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -53.60 +/- 72.37
+      value: -48.02 +/- 39.41
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 650000
-'learning_rate': 0.00025
+'total_timesteps': 450000
+'learning_rate': 0.00024
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1736775756.ee3f6528ecdd.23449.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127c06e0faa3d96b1db295b8561cd7dd4c6effb7d77ee14580a3b2f92f7ac6a2
+size 614983

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b0c89361356e3690ed63bea9b1f46719390ba92725f510461391ca9ecb8da0
+oid sha256:b6087e20074ed88de82914603d71cccb884b37339d12afda4349721b1fb3fd1b
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -53.59944449446043, "std_reward": 72.36732623180626, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-13T13:41:43.758614"}
+{"env_id": "LunarLander-v2", "mean_reward": -48.01649266588932, "std_reward": 39.41392776470939, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-13T13:55:30.801375"}