Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -99.09 +/- 72.98
+      value: -89.40 +/- 92.82
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 8
-'update_epochs': 8
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1716464697.98d39517c90d.23333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f746d18f54322921da7855b6b249b775ed2bdc9e48980383dd2b2bd4ae1f3e4
+size 196508

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b564c8ee1f9f5b64d45f3d981c247fbe1e5ae5b6eeec53ef282ede99f926c5
+oid sha256:a168efbaa199a3e8a3b9a054d7d4f93f2a4b8e0ced4ca5f4285e1f18c3f9dc39
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -99.09124368024084, "std_reward": 72.97544328839695, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:43:41.075919"}
+{"env_id": "LunarLander-v2", "mean_reward": -89.39829122257106, "std_reward": 92.82373938189099, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-23T11:46:32.856504"}