Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 53.63 +/- 161.79
+      value: -150.02 +/- 99.37
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 150000
-'learning_rate': 0.0025
+'total_timesteps': 300000
+'learning_rate': 2.5e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1710079064.Burak.19768.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d350388c359f6bb8ba032a1eba1e61979215e090e142345a74bc30a89c9ebc14
+size 667557

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49468edbc95d130c2f3abaeb5f930f8127f4bb90e10a64f7dfb637dee3bb12e7
+oid sha256:28438252276fa4ea22f9db712276c95e0e17427a48caf6bcd221c32c423dacf8
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 53.62912436228565, "std_reward": 161.79277945203984, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-10T16:56:07.489650"}
+{"env_id": "LunarLander-v2", "mean_reward": -150.01538213027925, "std_reward": 99.36987599739486, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-10T17:04:08.374193"}