Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -135.01 +/- 65.97
+      value: -172.65 +/- 92.01
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.95
+'gamma': 0.9
 'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1694597611.422f4b7e0f84.9302.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e834bd2f6bbdaa7d67a9e0e31e8e96a4095b2bf2ab43f7d1bce55ce9296b62
+size 132941

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ace0f90e0d3be42eb4e1e8e35e64f9beca39e5a8a1287113ff34c9ac84240b
+oid sha256:2af41d76611f3c0f9615f69eaccd54fc5e7c58f338864800bbab455f11cbddea
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -135.01267789093615, "std_reward": 65.96992797289683, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:32:29.080451"}
+{"env_id": "LunarLander-v2", "mean_reward": -172.64755265864335, "std_reward": 92.00983479410681, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:34:26.458092"}