Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -586.17 +/- 173.03
+      value: -124.76 +/- 40.56
       name: mean_reward
       verified: false
 ---
@@ -37,25 +37,25 @@ model-index:
 'wandb_entity': 'sw32-seo'
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 74969
-'learning_rate': 1.0077309193535382
-'num_envs': 8
-'num_steps': 256
+'total_timesteps': 37066
+'learning_rate': 1.0054877767970472
+'num_envs': 2
+'num_steps': 64
 'anneal_lr': True
 'gae': True
-'gamma': 0.9608675121488108
-'gae_lambda': 1.130431700684591
-'num_minibatches': 8
-'update_epochs': 5
+'gamma': 0.9139643960747568
+'gae_lambda': 1.221468199881571
+'num_minibatches': 2
+'update_epochs': 8
 'norm_adv': True
-'clip_coef': 0.10841843195379897
+'clip_coef': 0.2697556445035566
 'clip_vloss': True
-'ent_coef': 0.07255791796350568
-'vf_coef': 0.8113779139000747
-'max_grad_norm': 0.537455051132491
+'ent_coef': 0.08668191269399932
+'vf_coef': 0.35117447755275977
+'max_grad_norm': 0.8869468016306309
 'target_kl': None
 'repo_id': 'sw32-seo/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 256}
+'batch_size': 128
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1681836474.9d4ea9fde4e7.34407.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb4772e525c0b0b68f7d8c5a69bec9fa55146b9d560d07c46c97d57e65f294a
+size 214026

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff77d8c9cc9933ea2c711c59b4d6006f43d17c6213a8acfbeff09a9981374de
+oid sha256:0238c894168aaf202138ae1d4af3608be8069b4488fe77270f48e5b078b6ee28
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -586.1705439993491, "std_reward": 173.03379597928313, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T16:45:47.445884"}
+{"env_id": "LunarLander-v2", "mean_reward": -124.76076889699061, "std_reward": 40.55915500361142, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T16:49:06.435771"}