Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -171.97 +/- 82.18
+      value: -133.19 +/- 81.26
       name: mean_reward
       verified: false
 ---
@@ -45,7 +45,7 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.95
+'gae_lambda': 0.99
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1694596038.422f4b7e0f84.2656.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf1b09f33b77fee8bc1d4fff6d58b2c10503f896e9ed3bb5456bbd3c4f9649a
+size 142601

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25103491df9a78b1225af679bb82cc5230c5c10a69c27c21caaa3d72d022b4e5
+oid sha256:0605cafc4157031ffaf22900e6b639875cb21412f093baa39bc7b9de9d147a75
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -171.96616716453462, "std_reward": 82.18176670957914, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:04:34.146856"}
+{"env_id": "LunarLander-v2", "mean_reward": -133.19135216449413, "std_reward": 81.26476657822171, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:08:10.889711"}