Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -213.71 +/- 73.95
+      value: 148.25 +/- 119.88
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677456670.25f188cb86e1.43706.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74cc67839a4de7da6c08122ff30ca1f53f6c91e58722c875f5018a916d4423dd
+size 1363874

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e75f4b11f55461ced0426e3e88a1f6eeeeae0166ebf8a323ef36bee96c3b54f
+oid sha256:6cb0737f6845ed8170f6c0991ec58092649513a8e3acc13f79799492780d82fc
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -213.70794756589953, "std_reward": 73.95184436930808, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T00:10:23.083066"}
+{"env_id": "LunarLander-v2", "mean_reward": 148.24975951966937, "std_reward": 119.87536434353854, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T00:33:05.159835"}