Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -112.38 +/- 65.44
+      value: -226.61 +/- 112.82
       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': 8
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1707828315.d2b834586242.4233.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf1df68cc4b63e29dd24fb4064b096002e5292159ba012daa207343991d0416
+size 100063

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:0c7298c243bd5a184a1b14d0dd367cb2d49d1c3022821c6816fa5ae613f42fb9
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -112.37707204691166, "std_reward": 65.43959672521734, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-13T12:43:14.574770"}
+{"env_id": "LunarLander-v2", "mean_reward": -226.6081844579334, "std_reward": 112.82376675590085, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-13T12:46:05.430260"}