Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 6.03 +/- 78.05
+      value: 53.90 +/- 68.09
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
-'learning_rate': 0.00025
+'total_timesteps': 750000
+'learning_rate': 0.0001
 'num_envs': 16
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.9995
+'gamma': 0.995
 'gae_lambda': 0.97
 'num_minibatches': 64
-'update_epochs': 4
+'update_epochs': 5
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1728033939.32e588a9c7ee.23809.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7f94899ee36e4a8a484b4a95a22650d30b5c901ac7bc30ebf17dd49d678fde
+size 294915

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d5c83ba110110849ec52ef8cc49dd476dc2ae349e33dc4f35c61f69d3f3f63
+oid sha256:b37d9f63438e9733b5ee32786f9027af068d8ac68b2cb20dad79c7fe9372b694
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 6.029210496709192, "std_reward": 78.04807198260976, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-04T09:06:27.688221"}
+{"env_id": "LunarLander-v2", "mean_reward": 53.897051909951315, "std_reward": 68.08612532659888, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-04T09:40:23.619507"}