Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -200.64 +/- 119.96
+      value: 144.77 +/- 80.11
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 10000000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1694529517.7e99a561f500.2204.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b41afa938a6786ce3e8cf0d52fe30e4c98862ad8ecf08f12fa3e905d7e62b5
+size 3391859

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88382a16fb1d114b2170d0eb0fa9cfb86ce0da14ec652524a3746a92957c0d6
-size 42469
+oid sha256:024d48e724ccbea8527a008a65a77efe490801449864c8e7f1cbc8e4d102bf10
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -200.64399301423356, "std_reward": 119.96033592162883, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T14:25:50.888292"}
+{"env_id": "LunarLander-v2", "mean_reward": 144.77304518663797, "std_reward": 80.1087037178352, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T18:27:21.792365"}