Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -172.46 +/- 120.66
+      value: -156.48 +/- 60.81
       name: mean_reward
       verified: false
 ---
@@ -32,12 +32,12 @@ model-index:
 'seed': 1
 'torch_deterministic': True
 'cuda': True
-'track': False
+'track': True
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1743996546.d7995ab92217.10913.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af0465193922e1872ca66887df5422ece4aa3e25a10aba0d10ece528829b4b3
+size 228126

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3aa039f2cc2e400e9f5be639d7a7a5ec3771363054bd917285bbbe2dfc755ee
+oid sha256:bea467b241f45122a16dd2acd4696f890ed9842b07f2a00953202aa5ab0633d5
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -172.45774007519086, "std_reward": 120.66128049894806, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-07T03:20:35.117245"}
+{"env_id": "LunarLander-v2", "mean_reward": -156.47875683194206, "std_reward": 60.81316321948918, "n_evaluation_episodes": 10, "eval_datetime": "2025-04-07T03:30:27.512918"}