Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -169.73 +/- 96.53
+      value: -129.38 +/- 43.64
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 200000
-'learning_rate': 0.0001
+'learning_rate': 0.01
 'num_envs': 4
 'num_steps': 256
 'anneal_lr': True

logs/events.out.tfevents.1689491290.8981986e6198.33755.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859f1fba836a3ef404ae3e5ac99923b00566369f1e1cdf5ef44b7aefb2d0225e
+size 158747

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d48e06c7d6148401181153f1475ab8b0e5911286169190aca1d72cced70967
+oid sha256:6305e2d7123f017f3f5de5a7e09bdbfad724082be9632e34d23d490731e33a90
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -169.72708051838686, "std_reward": 96.52854253023148, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T07:04:17.030388"}
+{"env_id": "LunarLander-v2", "mean_reward": -129.38387550638123, "std_reward": 43.636298406401174, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T07:13:59.357655"}