Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -238.15 +/- 136.41
+      value: 150.82 +/- 117.27
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50
+'total_timesteps': 500000
 'learning_rate': 0.0025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677885853.0726c440142d.7366.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b00291e69da8eb33450e0ab294ce64b7939e799ee96bdc21c95fc35a69d56f7b
+size 648380

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:101150854b2b8737459c7dea8dede051ef3a05fb61b285d5cdbf6ef12c9b1ff5
+oid sha256:db8226ec4a337291f8702e955626af7f114545b762f2d8cfdbabd27b045ac2a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -238.15198583331335, "std_reward": 136.40547173873318, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T23:23:47.262047"}
+{"env_id": "LunarLander-v2", "mean_reward": 150.8157494956434, "std_reward": 117.27418484324271, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T23:35:22.283128"}