Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 132.41 +/- 47.16
+      value: 120.10 +/- 68.69
       name: mean_reward
       verified: false
 ---
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 1024
-'update_epochs': 6
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1688541123.0caa7588bd42.41031.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d280550fc6f792acac45f90c8ff39e8f73f9be27e820ad49bbdf1094842cd280
+size 375251

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c45613936aca4d106cf2fed73d089a2426d04abfb6a43b4ce95bc552af86792
+oid sha256:1fdf5ab0ebee91a0467eb9e1365d5ef34760a3cb2a30420e5e55ac79323cde28
 size 553317

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 132.4142827162276, "std_reward": 47.15530684566661, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-05T06:54:56.763750"}
+{"env_id": "LunarLander-v2", "mean_reward": 120.09965251595543, "std_reward": 68.69080797907064, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-05T07:51:22.294350"}