Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -156.27 +/- 126.33
+      value: -112.93 +/- 95.43
       name: mean_reward
       verified: false
 ---
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.3
+'clip_coef': 0.7
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1677345734.d57c8ab0d1e2.16361.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977aec72f02ecfc48e58aef68ef003c6c5f2ebee15b09ca8dd9bbdc29cf124b7
+size 104102

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c7d9f37344454cd2bd1175f3f4463b9643398dc56b58eec661bc6eb2d7df7f
+oid sha256:169acbbfab735236e727bdcd143764cecb2e4a8b3fc00c4664c7bb56fe7a8c8b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -156.2731059934304, "std_reward": 126.33083285889653, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-25T17:21:54.795514"}
+{"env_id": "LunarLander-v2", "mean_reward": -112.9296746866612, "std_reward": 95.42571779378683, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-25T17:22:58.928477"}