Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -3.61 +/- 82.38
+      value: 76.30 +/- 141.22
       name: mean_reward
       verified: false
 ---
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.25
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1682862821.73e30408940d.17660.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2feb7e19673a15b515a214f302ca099412875ccea68539e82a4a0f12cb8b927
+size 257256

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aca9fd39dbb89249456292aafcb07146b7621e7f243ab1a65691b0a37dea354
+oid sha256:7c9ec9789c1b91b8706ff41c217551dfcfe2137d1cc1beb478cbef9d4c674082
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -3.609234286727279, "std_reward": 82.37968111976762, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T13:52:54.710870"}
+{"env_id": "LunarLander-v2", "mean_reward": 76.30248581195453, "std_reward": 141.22261457039272, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T13:58:48.750791"}