hongshaorou/reinforcement_learning_truly_ppo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

delete unused utils

Browse Source
This commit is contained in:
Nugroho Dewantoro 2020-12-31 09:15:21 +08:00
parent 9c801f0adc
commit cdb2472ac7
3 changed files with 0 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
PPO/pytorch/ppo_pytorch.py
View File

@ -18,16 +18,6 @@ import datetime
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
dataType = torch.cuda.FloatTensor if torch.cuda.is_available() else torch.FloatTensor dataType = torch.cuda.FloatTensor if torch.cuda.is_available() else torch.FloatTensor
class Utils():
def prepro(self, I):
I = I[35:195] # crop
I = I[::2,::2, 0] # downsample by factor of 2
I[I == 144] = 0 # erase background (background type 1)
I[I == 109] = 0 # erase background (background type 2)
I[I != 0] = 1 # everything else (paddles, ball) just set to 1
X = I.astype(np.float32).ravel() # Combine items in 1 array
return X
class Actor_Model(nn.Module): class Actor_Model(nn.Module):
def __init__(self, state_dim, action_dim): def __init__(self, state_dim, action_dim):
super(Actor_Model, self).__init__() super(Actor_Model, self).__init__()

10
PPO/tensorflow 2/ppo_tensorflow.py
View File

@ -11,16 +11,6 @@ import numpy as np
import sys import sys
import numpy import numpy
class Utils():
def prepro(self, I):
I = I[35:195] # crop
I = I[::2,::2, 0] # downsample by factor of 2
I[I == 144] = 0 # erase background (background type 1)
I[I == 109] = 0 # erase background (background type 2)
I[I != 0] = 1 # everything else (paddles, ball) just set to 1
X = I.astype(np.float32).ravel() # Combine items in 1 array
return X
class Actor_Model(Model): class Actor_Model(Model):
def __init__(self, state_dim, action_dim): def __init__(self, state_dim, action_dim):
super(Actor_Model, self).__init__() super(Actor_Model, self).__init__()

10
PPO_continous/tensorflow/ppo_continous_tensorflow.py
View File

@ -11,16 +11,6 @@ import numpy as np
import sys import sys
import numpy import numpy
class Utils():
def prepro(self, I):
I = I[35:195] # crop
I = I[::2,::2, 0] # downsample by factor of 2
I[I == 144] = 0 # erase background (background type 1)
I[I == 109] = 0 # erase background (background type 2)
I[I != 0] = 1 # everything else (paddles, ball) just set to 1
X = I.astype(np.float32).ravel() # Combine items in 1 array
return X
class Actor_Model(Model): class Actor_Model(Model):
def __init__(self, state_dim, action_dim): def __init__(self, state_dim, action_dim):
super(Actor_Model, self).__init__() super(Actor_Model, self).__init__()