Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -199.43 +/- 118.10
+      value: -118.44 +/- 26.43
       name: mean_reward
       verified: false
 ---
@@ -44,8 +44,8 @@ model-index:
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.999
-'gae_lambda': 0.98
+'gamma': 0.9999
+'gae_lambda': 0.99
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1694592760.90c1b31fa24d.2133.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec8da900c4ab7e8c261b27a045f59fbc57dd6959eb438cee94f68bffc97e36a
+size 142719

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0abad7b782e3f9211f6661be300830dbc09760ce9c1906d33ba5bfd09209e3
+oid sha256:fb2bf27dbc6e37224bd159514307e4a23e1a66fa116b7612364c27ed8e45409b
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -199.42643945785275, "std_reward": 118.09537541111304, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T21:10:19.021390"}
+{"env_id": "LunarLander-v2", "mean_reward": -118.4360627649576, "std_reward": 26.428798009569075, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T08:13:41.907089"}