Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -102.79 +/- 49.64
+      value: -99.09 +/- 72.98
       name: mean_reward
       verified: false
 ---
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 8
-'update_epochs': 4
+'update_epochs': 8
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1716464558.98d39517c90d.22746.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ad16dea8edba3ac529d5e10241f5c60751add9b6e8bce308c2dd7b02d8cab2
+size 97591

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e26e3e2b35e109ddde8a86b1dcda3ce795ac587502f602cb2fbc7a9ed9e9eb
+oid sha256:e7b564c8ee1f9f5b64d45f3d981c247fbe1e5ae5b6eeec53ef282ede99f926c5
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -102.78620665280528, "std_reward": 49.63993503762939, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:38:46.733238"}
+{"env_id": "LunarLander-v2", "mean_reward": -99.09124368024084, "std_reward": 72.97544328839695, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:43:41.075919"}