Commit a66420c7 authored by Dipam Chakraborty's avatar Dipam Chakraborty
Browse files

lr sched exp

parent e8e41b76
......@@ -341,15 +341,14 @@ class CustomTorchPolicy(TorchPolicy):
return False
def update_lr(self):
if self.config['lr_schedule']:
# self.lr = 0.997 * self.lr
# if self.timesteps_total - self.best_rew_tsteps > 1e6:
# self.best_rew_tsteps = self.timesteps_total
# self.lr = self.lr * 0.6
if self.config['lr_schedule'] == 'linear':
self.lr = linear_schedule(initial_val=self.config['lr'],
final_val=self.config['final_lr'],
current_steps=self.timesteps_total,
total_steps=self.target_timesteps)
elif self.config['lr_schedule'] == 'exponential':
self.lr = 0.997 * self.lr
def update_ent_coef(self):
if self.config['entropy_schedule']:
......
......@@ -54,7 +54,7 @@ procgen-ppo:
adaptive_gamma: False
final_lr: 2.0e-4
lr_schedule: True
lr_schedule: 'exponential'
final_entropy_coeff: 0.002
entropy_schedule: False
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment