Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -195.15 +/- 110.71
+      value: -16.04 +/- 46.29
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
-'learning_rate': 0.0001
+'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1676592454.16efff3e153a.16334.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3cfcd33661126898e2a0eabde059e8524598232a2b4a0a7cab89888bcdd41a
+size 338765

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca9520f11a44abc63e24b1f352bc7df41915e5c00647708761452f4d4a63f25
+oid sha256:130267ed6be293e08f2610e4a2dedb99da2f4b413a3a0e448dc713772dc4f13c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -195.1521995339753, "std_reward": 110.70849349912875, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T00:06:51.664419"}
+{"env_id": "LunarLander-v2", "mean_reward": -16.038426443478365, "std_reward": 46.28728191684836, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T00:17:49.658235"}