Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -124.76 +/- 40.56
+      value: -1167.27 +/- 1106.76
       name: mean_reward
       verified: false
 ---
@@ -37,25 +37,25 @@ model-index:
 'wandb_entity': 'sw32-seo'
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 37066
-'learning_rate': 1.0054877767970472
+'total_timesteps': 67246
+'learning_rate': 1.001427335451286
 'num_envs': 2
 'num_steps': 64
 'anneal_lr': True
 'gae': True
-'gamma': 0.9139643960747568
-'gae_lambda': 1.221468199881571
-'num_minibatches': 2
-'update_epochs': 8
+'gamma': 0.9437592340075336
+'gae_lambda': 1.8061770101450632
+'num_minibatches': 8
+'update_epochs': 7
 'norm_adv': True
-'clip_coef': 0.2697556445035566
+'clip_coef': 0.21454601256391767
 'clip_vloss': True
-'ent_coef': 0.08668191269399932
-'vf_coef': 0.35117447755275977
-'max_grad_norm': 0.8869468016306309
+'ent_coef': 0.05650145521486992
+'vf_coef': 0.20954107655236845
+'max_grad_norm': 0.889870162839866
 'target_kl': None
 'repo_id': 'sw32-seo/ppo-LunarLander-v2'
 'batch_size': 128
-'minibatch_size': 64}
+'minibatch_size': 16}
   ```
   

logs/events.out.tfevents.1681837356.27b90b36cb11.2052.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d47863df7630c27a7612b5d5156d340da4a7b3a8206f766712d28a679036d5b
+size 336402

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0238c894168aaf202138ae1d4af3608be8069b4488fe77270f48e5b078b6ee28
+oid sha256:3d1a83e51605e710651e64cdb321ce6d8d2c31da8ae7c224d1b9b98e5e1be468
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -124.76076889699061, "std_reward": 40.55915500361142, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T16:49:06.435771"}
+{"env_id": "LunarLander-v2", "mean_reward": -1167.2678529623365, "std_reward": 1106.7607285892195, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T17:06:58.398598"}