Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -151.74 +/- 114.29
+      value: -75.02 +/- 111.93
       name: mean_reward
       verified: false
 ---
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 12
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1691304321.70c07b9c2426.19961.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d82290f0e0c91d2ff03b8f9c3f0b6cc7b61dd1de97e684a12cd28d19fbba1b
+size 132104

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd70ac2abe8388e47ebc462eed3957818d5442f26d6067f11199f302095d3eb4
+oid sha256:4367bb5cb928cf18f592a790b0b2734592884fc1b8c81a3b0a6bf0c1ae652792
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -151.74119369568973, "std_reward": 114.28964840480404, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-06T06:37:50.628979"}
+{"env_id": "LunarLander-v2", "mean_reward": -75.01622119585815, "std_reward": 111.93228129677537, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-06T06:46:37.894867"}