Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -191.20 +/- 112.70
+      value: -189.77 +/- 129.31
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 500
+'total_timesteps': 100000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1676639811.4eae8d4ce8b9.11196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8751ef13b5b9e75af84a62653c1305d1eb6f36ce70d4f0d261536d917f3d6bdb
+size 211139

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63769f9e437caca2c4810599876d70e100707b83852eae9e53ce8bca8f31a37e
+oid sha256:1837fb9ff64c19ac0c8a7e1a5dc8903cab9df1c344a143c8f22e14c4b113ba6d
 size 42597

results.json

@@ -1 +1 @@
-{"gym_id": "LunarLander-v2", "mean_reward": -191.2044438197692, "std_reward": 112.7004549247968, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T13:16:25.935391"}
+{"gym_id": "LunarLander-v2", "mean_reward": -189.76607684633547, "std_reward": 129.31463973216373, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T13:18:15.251101"}