Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 76.30 +/- 141.22
+      value: 63.74 +/- 119.91
       name: mean_reward
       verified: false
 ---
@@ -44,11 +44,11 @@ model-index:
 'num_steps': 128
 'anneal_lr': True
 'gamma': 0.99
-'gae_lambda': 0.95
+'gae_lambda': 0.97
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.25
+'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1682863425.73e30408940d.20194.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b8e24d58001965b1d75da12a484ed7b3b6fa882a34522f1eee59fec2737690
+size 273895

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9ec9789c1b91b8706ff41c217551dfcfe2137d1cc1beb478cbef9d4c674082
+oid sha256:3d68c62d48dcd5c5af6b90efddb068633afea6b687532c722b83ca2defe4773b
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 76.30248581195453, "std_reward": 141.22261457039272, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T13:58:48.750791"}
+{"env_id": "LunarLander-v2", "mean_reward": 63.74276193049923, "std_reward": 119.910189413978, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T14:08:37.377004"}