Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -198.06 +/- 109.63
+      value: -238.19 +/- 127.44
       name: mean_reward
       verified: false
 ---
@@ -50,7 +50,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.05
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.001
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1685093958.2850cb3f29b2.19555.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6994409eceb6d9b4e21335aa9574991a03594b2d8161d517fe146bd161acf62
+size 62777

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1691b0ac62d4f07f397614fceabacb0b78db867359737b6ade507380bfecab
+oid sha256:bc1ca0816c8190971476add636ea4ea749ae968789c288e437be9fe7b503d716
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -198.06125024553063, "std_reward": 109.62839906232786, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:37:56.419974"}
+{"env_id": "LunarLander-v2", "mean_reward": -238.19394135070834, "std_reward": 127.44228544578107, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:39:38.130834"}