Merge pull request #418 from kywch/quick

Small changes to pufferl

Author: jsuarez5341

pufferlib/config/default.ini

@@ -29,7 +29,7 @@ precision = float32
 total_timesteps = 10_000_000
 learning_rate = 0.015
 anneal_lr = True
-min_learning_rate = 0.0
+min_lr_ratio = 0.0
 gamma = 0.995
 gae_lambda = 0.90
 update_epochs = 1

pufferlib/config/ocean/g2048.ini

@@ -26,7 +26,7 @@ snake_reward_weight = 0.0005
 # 512 hidden: https://wandb.ai/kywch/pufferlib/runs/5thsjr61?nw=nwuserkywch
 total_timesteps = 6_767_676_767
 anneal_lr = True
-min_learning_rate = 0.00005
+min_lr_ratio = 0.15
 batch_size = auto
 bptt_horizon = 64
 minibatch_size = 32768

pufferlib/pufferl.py

@@ -184,8 +184,9 @@ def __init__(self, config, vecenv, policy, logger=None):
 
         # Learning rate scheduler
         epochs = config['total_timesteps'] // config['batch_size']
+        eta_min = config['learning_rate'] * config['min_lr_ratio']
         self.scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
-            optimizer, T_max=epochs, eta_min=config['min_learning_rate'])
+            optimizer, T_max=epochs, eta_min=eta_min)
         self.total_epochs = epochs
 
         # Automatic mixed precision
@@ -879,6 +880,7 @@ def __init__(self, args, load_id=None, resume='allow'):
             resume=resume,
             config=args,
             tags = [args['tag']] if args['tag'] is not None else [],
+            settings=wandb.Settings(console="off"),  # stop sending dashboard to wandb
         )
         self.wandb = wandb
         self.run_id = wandb.run.id