Pneuma/pneuma-pygame
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Increased size of NNs, and switched critic to 2nd GPU

Browse source
This commit is contained in:
Vasilis Valatsos 2024-03-11 12:44:20 +02:00
parent 3324e092ef
commit e804ee729d
1 changed files with 7 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
ml/ppo/brain.py
View file

@ -52,7 +52,7 @@ class PPOMemory:
class ActorNetwork(nn.Module): class ActorNetwork(nn.Module):
def __init__(self, input_dim, output_dim, alpha, fc1_dims=512, fc2_dims=512, chkpt_dir='tmp'): def __init__(self, input_dim, output_dim, alpha, fc1_dims=1024, fc2_dims=1024, chkpt_dir='tmp'):
super(ActorNetwork, self).__init__() super(ActorNetwork, self).__init__()
self.chkpt_dir = chkpt_dir self.chkpt_dir = chkpt_dir
@ -92,7 +92,7 @@ class ActorNetwork(nn.Module):
class CriticNetwork(nn.Module): class CriticNetwork(nn.Module):
def __init__(self, input_dims, alpha, fc1_dims=2048, fc2_dims=2048, chkpt_dir='tmp'): def __init__(self, input_dims, alpha, fc1_dims=4096, fc2_dims=4096, chkpt_dir='tmp'):
super(CriticNetwork, self).__init__() super(CriticNetwork, self).__init__()
self.chkpt_dir = chkpt_dir self.chkpt_dir = chkpt_dir
@ -106,10 +106,10 @@ class CriticNetwork(nn.Module):
nn.LeakyReLU(), nn.LeakyReLU(),
nn.Linear(fc1_dims, fc2_dims), nn.Linear(fc1_dims, fc2_dims),
nn.LeakyReLU(), nn.LeakyReLU(),
# nn.Linear(fc1_dims, fc2_dims), nn.Linear(fc1_dims, fc2_dims),
# nn.LeakyReLU(), nn.LeakyReLU(),
# nn.Linear(fc1_dims, fc2_dims), nn.Linear(fc1_dims, fc2_dims),
# nn.LeakyReLU(), nn.LeakyReLU(),
nn.Linear(fc1_dims, fc2_dims), nn.Linear(fc1_dims, fc2_dims),
nn.LeakyReLU(), nn.LeakyReLU(),
nn.Linear(fc2_dims, 1) nn.Linear(fc2_dims, 1)
@ -117,7 +117,7 @@ class CriticNetwork(nn.Module):
self.optimizer = optim.Adam(self.parameters(), lr=alpha, betas=(0.9, 0.9), eps=1e-5) self.optimizer = optim.Adam(self.parameters(), lr=alpha, betas=(0.9, 0.9), eps=1e-5)
self.device = T.device('cuda:0' if T.cuda.is_available() else 'cpu') self.device = T.device('cuda:1' if T.cuda.is_available() else 'cpu')
self.to(self.device) self.to(self.device)