Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -129.38 +/- 43.64
+      value: -81.01 +/- 14.53
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 200000
-'learning_rate': 0.01
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 256
 'anneal_lr': True
@@ -53,7 +53,7 @@ model-index:
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
-'target_kl': None
+'target_kl': 0.015
 'repo_id': 'Hans14/LunarLander-v2'
 'batch_size': 1024
 'minibatch_size': 256}

logs/events.out.tfevents.1689491827.8981986e6198.36107.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863e626f6b6d31d8db8a4f36d1ff8bd6b291d3923d8b6ee5d779df22c15c578c
+size 157267

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6305e2d7123f017f3f5de5a7e09bdbfad724082be9632e34d23d490731e33a90
+oid sha256:b4c4f34020cf2c50d62ec6986c6ad136135d52f017f47f9c3f13f9f207e3b068
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -129.38387550638123, "std_reward": 43.636298406401174, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T07:13:59.357655"}
+{"env_id": "LunarLander-v2", "mean_reward": -81.01337020748892, "std_reward": 14.52916289685471, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-16T07:23:51.838025"}