Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -57.91 +/- 159.02
+      value: -15.39 +/- 187.56
       name: mean_reward
       verified: false
 ---
@@ -43,12 +43,12 @@ model-index:
 'num_steps': 512
 'anneal_lr': True
 'gae': True
-'gamma': 0.7
-'gae_lambda': 0.7
+'gamma': 0.5
+'gae_lambda': 0.5
 'num_minibatches': 64
 'update_epochs': 64
 'norm_adv': True
-'clip_coef': 0.5
+'clip_coef': 2.0
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1699878486.32527197bbe9.8365.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6b0e081f45edf19d17a14945d6d365cd30a25ad527d0594b86eee7daa10832
+size 173296

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4024eec63284276aae2695ca6faa87de6fcce3c1fc48f76a97091e5ddc6da52f
+oid sha256:2090e8a2d368da53b9285c46a2f8045468452d8d2348269d98267a4a3f159a02
 size 80402

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -57.91068122462283, "std_reward": 159.02319510359266, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-13T12:27:12.875632"}
+{"env_id": "LunarLander-v2", "mean_reward": -15.388651850510598, "std_reward": 187.56029215942235, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-13T12:39:52.486758"}