Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -136.70 +/- 64.03
+      value: -145.16 +/- 65.84
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.999
+'gamma': 0.98
 'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1694597362.422f4b7e0f84.8228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89434c8f397255d4ff420e8c71c90592b623a5a75664fb0e6ad54ae88b1a0a42
+size 138502

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebf3465c38ec32051261e720f626890cc85ca8688e353209b67003d4a9114ce
+oid sha256:0f0a69c9772c9c455e8a97eabf503a3d78e626deeaace112e1766c1151182bde
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -136.70251694105684, "std_reward": 64.02571409714388, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:27:41.162511"}
+{"env_id": "LunarLander-v2", "mean_reward": -145.16047759050534, "std_reward": 65.83531174221363, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:30:16.277926"}