Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -1.74 +/- 68.05
+      value: 44.96 +/- 63.06
       name: mean_reward
       verified: false
 ---
@@ -50,7 +50,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.03
+'ent_coef': 0.02
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1689918455.2364148aff98.5380.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32c3fc034ae758ac1d43913fbc4e3e1ce3b58b4efdf29f036be3c47fd432ccb
+size 160747

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9258b5833371718b1ea42a9618208402533883c972690ccac738aeea863cfb1e
+oid sha256:8a0c687efeb66c26f44e6dba9bf556f90a2c890bb5d59eef3046b448c101c1e3
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -1.7415937480253632, "std_reward": 68.04936794891167, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-21T05:45:41.805245"}
+{"env_id": "LunarLander-v2", "mean_reward": 44.9559902948874, "std_reward": 63.060724461389356, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-21T05:53:30.458452"}