Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.23 +/- 124.77
+      value: -74.94 +/- 50.35
       name: mean_reward
       verified: false
 ---
@@ -33,7 +33,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1702128701.1bb5be1b74f4.24051.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088f25357091ab60c6be7c788ecf491af24f5fcdf718b4c646ffd01c41a1101f
+size 1235349

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:4bab62617dee61f1306b075d08c5031f47552a39ea30c380840904fab1b528b7
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -150.2339901580266, "std_reward": 124.76600063475999, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-09T12:50:32.179768"}
+{"env_id": "LunarLander-v2", "mean_reward": -74.94311317343826, "std_reward": 50.34870151027525, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-09T14:00:53.469819"}