Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -103.78 +/- 120.25
+      value: -90.99 +/- 65.99
       name: mean_reward
       verified: false
 ---
@@ -37,15 +37,15 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 16
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.95
-'num_minibatches': 128
+'num_minibatches': 256
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'zzen0008/ppo-LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 32}
+'batch_size': 16384
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1678601845.ZZDev.84170.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204d66b1f2956ac0b658ebfe004af70f3e7cb6714558fe4b9e8d89984b4d48ae
+size 110853

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8859b41c7dcd894e74231cc88bc1bcefe2de395e562acbef17543ea06e1226ef
+oid sha256:d7fbc9f28661500b2fc0a10797838bf27b6705487695fdd6ccab7db82905043a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -103.77534680071457, "std_reward": 120.24842976601826, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T17:14:39.216282"}
+{"env_id": "LunarLander-v2", "mean_reward": -90.98581989394988, "std_reward": 65.9903379112763, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T17:18:19.841517"}