Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -19.44 +/- 112.71
+      value: 9.40 +/- 51.21
       name: mean_reward
       verified: false
 ---
@@ -51,7 +51,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.005
+'ent_coef': 0.0005
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1691894454.4c5d58e91a6c.225.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bccaad9ff8022364e5b9d33cd41590e7070e1f13e6519a147cbeef90b46c40d4
+size 138424

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7014ce45d24c2ceac222d20171ab69e6c5b0317b08e32ac9a22a0d5e10505ef
+oid sha256:5ef1068c332f17e5bdc476fdfcbe39f4818441458145faffb65e9e609660a121
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -19.440788101191153, "std_reward": 112.71072222129561, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:40:32.416642"}
+{"env_id": "LunarLander-v2", "mean_reward": 9.400729433379885, "std_reward": 51.212038162468836, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:44:17.144996"}