Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 101.89 +/- 61.28
+      value: 195.84 +/- 80.51
       name: mean_reward
       verified: false
 ---
@@ -35,27 +35,27 @@ model-index:
 'track': False
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
-'capture_video': True
+'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1500000
-'learning_rate': 0.0001
+'total_timesteps': 1000000
+'learning_rate': 0.0003
 'num_envs': 4
-'num_steps': 2048
+'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.999
-'gae_lambda': 0.98
-'num_minibatches': 32
+'gamma': 0.995
+'gae_lambda': 0.95
+'num_minibatches': 4
 'update_epochs': 10
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.001
-'vf_coef': 0.7
+'ent_coef': 0.005
+'vf_coef': 0.5
 'max_grad_norm': 0.5
-'target_kl': 0.01
+'target_kl': 0.02
 'repo_id': 'alexchilton/lunarlanding-v2'
-'batch_size': 8192
-'minibatch_size': 256}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1739869025.MacBookPro.1945.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f01c8b5761da8dc82c23816a395c1405b7a039c7c8b209a4bb16eac094ffef4
+size 1320189

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6cff44df1bb1160146e7f7acc8e9b13e7e5ba65fac63f18346857ffdf48470
+oid sha256:928c10d7fd80e507c638aabf795f8921fba09a0007eb6e7bd30686e486296ded
 size 42898

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2decdffeab8d886c90dd5d92b4774a13676f3b270580a194e6496f9dc80cfd82
-size 180999
+oid sha256:68b935785f894014d113c8c70a9ebf7f4d848d4cf03326e3021bb2d20a13894a
+size 70051

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 101.88822004952031, "std_reward": 61.283516924229104, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-18T09:55:59.930880"}
+{"env_id": "LunarLander-v2", "mean_reward": 195.8408745657809, "std_reward": 80.51279738011101, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-18T10:07:33.520378"}