Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -15.39 +/- 187.56
+      value: 97.92 +/- 98.65
       name: mean_reward
       verified: false
 ---
@@ -43,12 +43,12 @@ model-index:
 'num_steps': 512
 'anneal_lr': True
 'gae': True
-'gamma': 0.5
-'gae_lambda': 0.5
+'gamma': 0.99
+'gae_lambda': 0.95
 'num_minibatches': 64
 'update_epochs': 64
 'norm_adv': True
-'clip_coef': 2.0
+'clip_coef': 5.0
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1699879248.32527197bbe9.11561.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e1756799a864b3e7b7655d5dc9eefd01e4d363c02f42ed71b00ab57ada2726
+size 117498

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2090e8a2d368da53b9285c46a2f8045468452d8d2348269d98267a4a3f159a02
+oid sha256:58bb932fed2741352988345b2ea1bce736d45535fd9229284716d3a48558539d
 size 80402

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -15.388651850510598, "std_reward": 187.56029215942235, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-13T12:39:52.486758"}
+{"env_id": "LunarLander-v2", "mean_reward": 97.92185554587627, "std_reward": 98.6527904973274, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-13T12:55:40.553439"}