Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -102.52 +/- 27.00
+      value: -180.62 +/- 112.47
       name: mean_reward
       verified: false
 ---
@@ -49,7 +49,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.15
+'clip_coef': 0.25
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1694551555.17a722d28ef8.5989.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:967cce0f68e7784d69dc14e85a2fcbaee85f79394d923c3135765475ecec697c
+size 72057

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05bef18e4e8f91309140caa4f3bf5ce9e5aff0ead99b807c295091db3bfa81c7
+oid sha256:bfafa5d43491669f8bbac35f60f8ee34cef1d0c4f737681fe97e933080720b43
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -102.52463681185324, "std_reward": 26.997907673140514, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:43:41.154021"}
+{"env_id": "LunarLander-v2", "mean_reward": -180.6237064665993, "std_reward": 112.46727911624386, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:46:35.942192"}