Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -130.31 +/- 81.32
+      value: -9.39 +/- 78.05
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1676630520.bdf54092a4ef.1729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ae29dc57f1a6384b9b27067a3f3ff3232e310285d53bc4d472abaaf98b2e69
+size 658578

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:600a312f67eb1d1b4f09a512dbdc63169bdfd520e9315f53e0039492a38fb5c4
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -130.30700034819543, "std_reward": 81.32468691522263, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T05:11:38.894604"}
+{"env_id": "LunarLander-v2", "mean_reward": -9.389997073335959, "std_reward": 78.05349964086047, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T10:58:15.047390"}