Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -66.84 +/- 63.69
+      value: -195.15 +/- 110.71
       name: mean_reward
       verified: false
 ---
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.3
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1676592211.16efff3e153a.15298.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb8632177c771b302c0f7fb7199b2b1459557f14213a38e89cc63ae7177ec76
+size 659670

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09959bf881bcb01e400be20167885f7b0f154b80be72cf081ca34722c4317a00
+oid sha256:aca9520f11a44abc63e24b1f352bc7df41915e5c00647708761452f4d4a63f25
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -66.8426411104437, "std_reward": 63.691851247331954, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T00:01:42.190356"}
+{"env_id": "LunarLander-v2", "mean_reward": -195.1521995339753, "std_reward": 110.70849349912875, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T00:06:51.664419"}