Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -156.84 +/- 68.01
+      value: -154.66 +/- 91.75
       name: mean_reward
       verified: false
 ---
@@ -50,7 +50,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.05
+'ent_coef': 0.5
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1698071200.527fe3665085.19192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51f96ce93844a84ffa3534fddd0e05c1248e6cbebdb36723a28a85a552864a3
+size 880777

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb9866b1ef0934d0a4d11aac5359c79822a9e609c18874326fbc774a9fbcc2e
+oid sha256:f67e935f7993924b75fa144025f8aeaf9dabf4d467736b3373ed5da14782f77e
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -156.84411362634867, "std_reward": 68.01235352547111, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:26:10.119748"}
+{"env_id": "LunarLander-v2", "mean_reward": -154.65525397827173, "std_reward": 91.74715553996019, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:31:12.787699"}