Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -132.54 +/- 65.07
+      value: -212.96 +/- 110.81
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 10000
-'learning_rate': 0.0025
+'learning_rate': 0.025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1677780356.6c4e5c51f044.15591.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3700ff15102377b09f8bc19011fe419c2af478d0bdfd29a580a02b0e055b9ed3
+size 20548

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d99450eeef21ff8ebd041bf1397e3f4eae82d29cc72413d5b2ba4132436b43fe
+oid sha256:290fc01ffdbcd7529ceddc2e5b96d28fbe9735ba5bb98f72d4e6f9fac78d71b1
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -132.5370606273601, "std_reward": 65.07467902019607, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:05:20.009588"}
+{"env_id": "LunarLander-v2", "mean_reward": -212.96045972546025, "std_reward": 110.80783724468003, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:06:12.242437"}