Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -169.55 +/- 71.57
+      value: -9.61 +/- 72.61
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1716531010.0949425aa1ca.33133.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f69384f72f141a62a770c731d8997dc02012d9cb765ec02a07898d5efb3115
+size 356304

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:1efdb17a91d165475a33b5df37ed9e8049c65b910cf084fd420eda94a1e63838
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -169.54980411338028, "std_reward": 71.57089161966397, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-24T06:07:35.655883"}
+{"env_id": "LunarLander-v2", "mean_reward": -9.60637939745944, "std_reward": 72.61200839800438, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-24T06:13:58.572315"}