Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -242.45 +/- 140.03
+      value: -172.06 +/- 53.62
       name: mean_reward
       verified: false
 ---
@@ -50,7 +50,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.005
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1735411110.2763f7ab14bb.6151.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43cb8029dfc6ad43b87e5f4599081ef77f4d10eba338952a4f2c53ea25b9f59
+size 113931

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ecb40165f04dad50e7307957e9d5011d2f0ad678b639759735a1f4524005e1d
+oid sha256:cc157e267c097626f32c6fc37e62b49ef307a0f59ac90936d5e7b07619fc461b
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -242.45051973379117, "std_reward": 140.02578871013702, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:29:21.185505"}
+{"env_id": "LunarLander-v2", "mean_reward": -172.06075819909432, "std_reward": 53.61607685641903, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:39:13.830362"}