Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 45.50 +/- 96.99
+      value: 62.98 +/- 67.06
       name: mean_reward
       verified: false
 ---
@@ -38,24 +38,24 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.001
-'num_envs': 2
-'num_steps': 16
+'learning_rate': 0.003
+'num_envs': 4
+'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.97
-'gae_lambda': 0.5
-'num_minibatches': 2
+'gamma': 0.999
+'gae_lambda': 0.98
+'num_minibatches': 4
 'update_epochs': 4
-'norm_adv': True
-'clip_coef': 0.05
-'clip_vloss': True
+'norm_adv': False
+'clip_coef': 0.2
+'clip_vloss': False
 'ent_coef': 0.01
-'vf_coef': 0.9
-'max_grad_norm': 0.3
-'target_kl': 0.1
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
 'repo_id': 'sw32-seo/ppo-LunarLander-v2'
-'batch_size': 32
-'minibatch_size': 16}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1682064588.SW-MacBook-Pro.local.34837.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e3c92f0f5eacc30221595e3b20493918bf72ee5351b92f10551e516f32c362
+size 81752

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4324fe9e12fb92273b0c2c17a869b7249c1ac2b527775d939456ccc6f858b43
+oid sha256:f34e16b4228849746efc18e095c68114097dbb3a149e3bb8c63e79f735a9aad5
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 45.50490040220389, "std_reward": 96.99241864332599, "n_evaluation_episodes": 50, "eval_datetime": "2023-04-21T16:29:00.727541"}
+{"env_id": "LunarLander-v2", "mean_reward": 62.98036793193456, "std_reward": 67.0600926762276, "n_evaluation_episodes": 50, "eval_datetime": "2023-04-21T17:11:26.768126"}