Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -183.85 +/- 147.03
+      value: -123.65 +/- 22.74
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.01
+'learning_rate': 0.005
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1696593531.Anderss-MacBook-Pro-4.local.42380.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3eed7c7719c007af35429939de1875be091b6cd6189fd86e1af197ab5d93d1
+size 131822

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2ad9b79124a608377795a8cb02f0cd66d81ddf7eaff3d41509793653162faf
+oid sha256:9c7e87f361ca6058820f76240a828d1b1e2253b98691690cc76f1238348b4daa
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -183.85407511163663, "std_reward": 147.03209188798937, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-06T13:57:48.637909"}
+{"env_id": "LunarLander-v2", "mean_reward": -123.65095444837365, "std_reward": 22.74334206356525, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-06T14:00:52.094519"}