Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -83.17 +/- 16.98
+      value: 54.10 +/- 62.79
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0013
+'learning_rate': 0.00101
 'num_envs': 5
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.91
+'gamma': 0.98
 'gae_lambda': 0.99
 'num_minibatches': 4
 'update_epochs': 5

logs/events.out.tfevents.1701202873.e705ad2e6486.25498.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf6116c1cd47ce166b6344f5ddb6f1c0434a57b2ef23ea91e40148519b2b103
+size 129901

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a5a5ed520ba9f7f20b8faff07f8fa029f63a6d1dc412ec8f6bb6f12ad7b5c8
+oid sha256:aa5d467572389f80ac7f0e821a34dfa4452bb190be7b6ea749486b2d377dfd71
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -83.1693124656219, "std_reward": 16.97639454517805, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:20:25.384152"}
+{"env_id": "LunarLander-v2", "mean_reward": 54.099372447684416, "std_reward": 62.79226573510771, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:24:11.332607"}