Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 38.61 +/- 117.37
+      value: 38.59 +/- 104.25
       name: mean_reward
       verified: false
 ---
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.5
+'clip_coef': 0.15
 'clip_vloss': False
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1692006875.c14e1bfbd2c3.18920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e789057a156a16a15dee2fc706cc3d8ed9434ad0f0686fe82006c6041c15379
+size 1297671

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80286643c9d8bca7a2adbac2ced3d6fc035f70028fafaa0474fab303e34fd61b
+oid sha256:3978c42bb26c4dba2181d0b1b46e24a504aafba45020f15954fb953ffe9260c4
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 38.61409593215818, "std_reward": 117.36882567256943, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T09:52:57.347255"}
+{"env_id": "LunarLander-v2", "mean_reward": 38.59408730366498, "std_reward": 104.25113810994253, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T10:25:16.904050"}