Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -98.18 +/- 101.27
+      value: -51.68 +/- 47.83
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.95
+'gae_lambda': 0.99
 'num_minibatches': 32
 'update_epochs': 10
 'norm_adv': True

logs/events.out.tfevents.1679878394.2a0c170730d9.71546.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03211e2ffdf699cc7bcbe78dfd91feb5b677bc0f1c685f322b4314f34f5623e
+size 110596

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba07d3b0a00b8f52a350a1b6cee7f11c27dd3bd27bdda98febb6627668384324
+oid sha256:efef603d9832ebdc3e76c0b2c4d23d3d1564421f210c806a5cced1d80463f694
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -98.18381635674903, "std_reward": 101.26577634798309, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:50:48.873008"}
+{"env_id": "LunarLander-v2", "mean_reward": -51.678503547439334, "std_reward": 47.8318744501941, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:55:02.277216"}