Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -186.25 +/- 106.45
+      value: -117.88 +/- 50.03
       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': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1685175519.711d0f4761a7.6806.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20541e6c2eb15750a873bd08de86ad43009bfc5f846edf5f1013842c5fbf6d70
+size 100886

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352b29f3c3f4d4e2a36b5743be7dd26cde2d9e8abe40e72c375dcb319e6f5ecc
+oid sha256:f4f0bc0f1503a07837560199df54821ffc0e0a4e66cafdfeaa50612bad3296e9
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -186.2505728019641, "std_reward": 106.44635816263965, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-27T08:17:38.048035"}
+{"env_id": "LunarLander-v2", "mean_reward": -117.87843888195323, "std_reward": 50.03356628985793, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-27T08:20:08.748752"}