Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -162.60 +/- 94.01
+      value: -144.86 +/- 69.98
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 7e-06
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1714949516.71d3fa3d3a00.20510.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766f11d4e1b97e26c6b9c918f7400ea373a26e85c03faff6be17ec7a06fa7a40
+size 221316

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bca388f3156436ed0f0d6d6ffcc739ae501296b718e9e71f2082f27339280f0
+oid sha256:bf4a7fde3320b1226867f811244d8c33574eca701ec88ceee90bda5c8724f5d8
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -162.60487179732635, "std_reward": 94.01477441131019, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:51:01.579522"}
+{"env_id": "LunarLander-v2", "mean_reward": -144.86024537047396, "std_reward": 69.9824089669883, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:53:17.855296"}