Merge branch 'master' into kernelfix

Author: javadr

beginner_source/dcgan_faces_tutorial.py

@@ -71,7 +71,7 @@
 # :math:`D` and :math:`G` play a minimax game in which :math:`D` tries to
 # maximize the probability it correctly classifies reals and fakes
 # (:math:`logD(x)`), and :math:`G` tries to minimize the probability that
-# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(x)))`).
+# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(z)))`).
 # From the paper, the GAN loss function is
 # 
 # .. math:: \underset{G}{\text{min}} \underset{D}{\text{max}}V(D,G) = \mathbb{E}_{x\sim p_{data}(x)}\big[logD(x)\big] + \mathbb{E}_{z\sim p_{z}(z)}\big[log(1-D(G(z)))\big]

intermediate_source/reinforcement_q_learning.py

@@ -63,7 +63,7 @@
 import numpy as np
 import matplotlib
 import matplotlib.pyplot as plt
-from collections import namedtuple
+from collections import namedtuple, deque
 from itertools import count
 from PIL import Image
 
@@ -115,16 +115,11 @@
 class ReplayMemory(object):
 
     def __init__(self, capacity):
-        self.capacity = capacity
-        self.memory = []
-        self.position = 0
+        self.memory = deque([],maxlen=capacity)
 
     def push(self, *args):
-        """Saves a transition."""
-        if len(self.memory) < self.capacity:
-            self.memory.append(None)
-        self.memory[self.position] = Transition(*args)
-        self.position = (self.position + 1) % self.capacity
+        """Save a transition"""
+        self.memory.append(Transition(*args))
 
     def sample(self, batch_size):
         return random.sample(self.memory, batch_size)