Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -213.18 +/- 148.25
+      value: -132.25 +/- 56.47
       name: mean_reward
       verified: false
 ---
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.38
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1694929795.ee290f883918.21960.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9f540172a96eee6a1d2907dad231e4bef739dbc78eef768bbaa1c220a085a3
+size 128467

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123b99bb32d2831a0ac8b11220b121d5fd0d28c31beefb871c2c014e4f45c225
+oid sha256:a0a24af05d8e1f58b4d6029d47959da57d5b382b7cfdef9c3049ffa6745f62b8
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -213.18445306743342, "std_reward": 148.2535319479413, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-17T05:49:15.128667"}
+{"env_id": "LunarLander-v2", "mean_reward": -132.24749001754472, "std_reward": 56.47402863189098, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-17T05:50:58.006509"}