Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -126.98 +/- 45.05
+      value: -195.78 +/- 125.20
       name: mean_reward
       verified: false
 ---
@@ -37,25 +37,25 @@ model-index:
 'wandb_entity': 'sw32-seo'
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 65411
-'learning_rate': 1.0014694907973054
-'num_envs': 8
-'num_steps': 256
+'total_timesteps': 41124
+'learning_rate': 1.001335050666658
+'num_envs': 2
+'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.930233257263184
-'gae_lambda': 0.4751629841147164
-'num_minibatches': 4
-'update_epochs': 4
+'gamma': 0.9679773026849
+'gae_lambda': 1.5193529129186465
+'num_minibatches': 8
+'update_epochs': 2
 'norm_adv': True
-'clip_coef': 0.2251066014107722
+'clip_coef': 0.36618698552096784
 'clip_vloss': True
-'ent_coef': 0.07231212485077365
-'vf_coef': 0.7166975503570835
-'max_grad_norm': 0.31925394607659835
+'ent_coef': 0.016994846815816388
+'vf_coef': 0.6263913978500655
+'max_grad_norm': 0.6525062174253925
 'target_kl': None
 'repo_id': 'sw32-seo/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 256
+'minibatch_size': 32}
   ```
   

logs/events.out.tfevents.1681834768.9d4ea9fde4e7.25755.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56d851bb36ba3212ee6ac4d34529269fb8702ac0cd6aeefe98e14bc55a99795
+size 136630

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5fefc6aba2d2ad139514fc91ce001d84f21928089e19f7fcefbe44d2081f1e3
+oid sha256:78a1829dadef577663132ee3672cbc59177e0cccd3beda3d261c8046d9486083
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -126.97579052057586, "std_reward": 45.04618938135841, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T16:18:55.455901"}
+{"env_id": "LunarLander-v2", "mean_reward": -195.78404439479374, "std_reward": 125.19987507529821, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T16:20:37.354024"}