Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -126.24 +/- 64.89
+      value: -102.52 +/- 27.00
       name: mean_reward
       verified: false
 ---
@@ -49,7 +49,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.15
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1694551389.17a722d28ef8.5294.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65849fa31c8ae3dd2deb0971630ba0a69c390b04bdae21904330841cd0138e5
+size 69963

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7daef2b47c97523a3d74b1f560816ff9f209db751eee0ba17016d5d2b24a3ad
+oid sha256:05bef18e4e8f91309140caa4f3bf5ce9e5aff0ead99b807c295091db3bfa81c7
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -126.24220068973128, "std_reward": 64.88954937922668, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:35:26.533104"}
+{"env_id": "LunarLander-v2", "mean_reward": -102.52463681185324, "std_reward": 26.997907673140514, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:43:41.154021"}