Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -128.94 +/- 87.14
+      value: -189.52 +/- 89.08
       name: mean_reward
       verified: false
 ---
@@ -44,13 +44,13 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.9
-'gae_lambda': 0.9
+'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 8
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.05
+'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1698072778.527fe3665085.25916.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71c2dad107f13d59d1a5980ca9c25641de44db54a357509397331035d0cc748
+size 102662

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa2f6fac6eb7b6411a0149a887c9f7ab56ee6f49340bc59ff494f622b2003c1
+oid sha256:e4b2597fbfa39796395fcd740a004c216c108e429a79d8560df69ee364f27f8b
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -128.9358893690048, "std_reward": 87.13581962908091, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:51:32.531005"}
+{"env_id": "LunarLander-v2", "mean_reward": -189.5197540517459, "std_reward": 89.077803164192, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:53:47.919341"}