Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 54.10 +/- 62.79
+      value: -20.02 +/- 121.08
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.98
-'gae_lambda': 0.99
+'gae_lambda': 0.85
 'num_minibatches': 4
 'update_epochs': 5
 'norm_adv': True

logs/events.out.tfevents.1701203120.e705ad2e6486.26521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47100f2936591a9ec1baa46c963fdbd175c4010fea3d9a170d19d1b9c518b9c0
+size 126679

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa5d467572389f80ac7f0e821a34dfa4452bb190be7b6ea749486b2d377dfd71
+oid sha256:abfddc6baa36d1faafc2a7ca6677f82558789af1c4f5c0d85eb0e20bfae19e0f
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 54.099372447684416, "std_reward": 62.79226573510771, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:24:11.332607"}
+{"env_id": "LunarLander-v2", "mean_reward": -20.01925307490944, "std_reward": 121.07507449825523, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:28:01.587184"}