Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -180.55 +/- 108.68
+      value: -191.30 +/- 117.76
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 5e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1714949792.71d3fa3d3a00.21752.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9208a283b72444b4ef8eea8c777acb0ff11e3794a61e83aa44a80f4d5e59ede7
+size 114299

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:0792a2b515886e3c981b32975c6cd623782aaf2e473ea4c69586eefe0ff8736b
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -180.55414330065565, "std_reward": 108.68069002480259, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:55:06.908732"}
+{"env_id": "LunarLander-v2", "mean_reward": -191.2986382309057, "std_reward": 117.76285338974455, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:57:13.155322"}