Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 64.69 +/- 15.69
+      value: 91.86 +/- 89.64
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.95
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1710259344.28d9d214646f.41290.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6445fd0b9fbea2c293f5a0c440a915836221fae68d13852b698958e073e8f3cc
+size 354206

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1275e8c779e237efeb16d984a3b4b26f5ca70c3673afbfae0d96181f636a99f9
+oid sha256:b30320340a7fc2835e739d77fb8939f30b91be927e2577bfd9b2f30c65607900
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 64.69184515009965, "std_reward": 15.691810262154094, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-12T15:51:20.436292"}
+{"env_id": "LunarLander-v2", "mean_reward": 91.86293564383529, "std_reward": 89.64152093353952, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-12T16:26:35.206529"}