Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.20 +/- 95.30
+      value: -110.99 +/- 83.90
       name: mean_reward
       verified: false
 ---
@@ -46,9 +46,9 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 16
+'update_epochs': 32
 'norm_adv': True
-'clip_coef': 0.05
+'clip_coef': 0.01
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1685095971.2850cb3f29b2.29238.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca3a3479a73bb20aa3dceeeba3a3e8e922aaaf73f4d451af05432b93c947636
+size 110471

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c6e25c4eb6cf4d491d438cc9082ac2c0675586c20e21f2bcfee8ab33b0c47a
+oid sha256:d7664452e77700ed1e8b1bdf813951628ec5060ca55323a4d0d6286c7ab12c3d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.2006583423907, "std_reward": 95.30287141570705, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:12:32.686112"}
+{"env_id": "LunarLander-v2", "mean_reward": -110.98683783991169, "std_reward": 83.9005254490006, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:14:20.490003"}