Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -189.66 +/- 87.04
+      value: 72.61 +/- 37.90
       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.1685014158.ea0ae8e4338b.18513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1e77476ab1ff5017ac5efc02a3e8eeee51c09118c30b84dfd5bb635e1a1458
+size 666941

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+oid sha256:2b9d543238803c060f8dbf5c92d5a1c98334eac95137b947dc15b59717d77604
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -189.66351093366762, "std_reward": 87.04133811537667, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-25T11:27:27.547309"}
+{"env_id": "LunarLander-v2", "mean_reward": 72.60946186758747, "std_reward": 37.90005290141124, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-25T11:46:40.768247"}