Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -227.55 +/- 121.09
+      value: -146.53 +/- 52.92
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 25000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677657501.75ced473f136.2716.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f571eb4cb59c685d689b1daaa430ed1a0c7f4cb6ca5fe5fee21fb91f6502a8
+size 55184

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a2eed28f19ea037a2de789fda2084683d46a4d25c7a38c0f25a049a4b0ce02
+oid sha256:500b10200ce0a800529bcedc1ad7e2918578606cb34569750159fa2fe5b22e04
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -227.55068191127754, "std_reward": 121.09323568736109, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T07:57:50.247712"}
+{"env_id": "LunarLander-v2", "mean_reward": -146.52614140763308, "std_reward": 52.9173637352744, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T07:58:44.716151"}