Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -167.01 +/- 86.97
+      value: -110.87 +/- 47.46
       name: mean_reward
       verified: false
 ---
@@ -34,7 +34,7 @@ model-index:
 'cuda': True
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1676822145.d4f51c055a2f.1.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7c26b6f8b0a07d4ddcea16ffcf176e6b3bb91682fc2d4bcd4a397c216809cf
+size 216752

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0d3b680e29b5b3446d6fe79791cff1378b38996436170c45a236584b5b7593
+oid sha256:f909290a6be75ca57c4d13ff61b2c226ff8838edd34a39b87664b495bd961fde
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -167.01109924061845, "std_reward": 86.97184842057882, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T15:53:39.958043"}
+{"env_id": "LunarLander-v2", "mean_reward": -110.87022887453995, "std_reward": 47.459516754489954, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T15:56:26.073483"}