update

Author: MorvanZhou

tutorial-contents/Evolution Strategy/(1+1)-ES.py

@@ -1,5 +1,7 @@
 """
-(1+1)-ES with 1/5th success rule
+(1+1)-ES with 1/5th success rule with visualization.
+
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
 """
 import numpy as np
 import matplotlib.pyplot as plt

tutorial-contents/Evolution Strategy/Evolution Strategy Basic.py

@@ -2,8 +2,10 @@
 The Evolution Strategy can be summarized as the following term:
 {mu/rho +, lambda}-ES
 
-Here we use:
+Here we use following term to find a maximum point.
 {n_pop/n_pop + n_kid}-ES
+
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
 """
 import numpy as np
 import matplotlib.pyplot as plt

tutorial-contents/Evolution Strategy/Natural Evolution Strategy (NES).py

@@ -1,4 +1,8 @@
 """
+The basic idea about Nature Evolution Strategy with visualation.
+
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
+
 Dependencies:
 Tensorflow >= r1.2
 numpy
@@ -14,8 +18,9 @@
 N_GENERATION = 100   # training step
 LR = 0.02            # learning rate
 
+
 # fitness function
-get_fitness = lambda pred: -((pred[:, 0])**2 + pred[:, 1]**2)
+def get_fitness(pred): return -((pred[:, 0])**2 + pred[:, 1]**2)
 
 # build multivariate distribution
 mean = tf.Variable(tf.random_normal([2, ], 13., 1.), dtype=tf.float32)

tutorial-contents/Genetic Algorithm/Find Path.py

@@ -1,3 +1,8 @@
+"""
+Visualize Genetic Algorithm to find a path to the target.
+
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
+"""
 import matplotlib.pyplot as plt
 import numpy as np
 

tutorial-contents/Genetic Algorithm/Genetic Algorithm Basic.py

@@ -1,3 +1,8 @@
+"""
+Visualize Genetic Algorithm to find a maximum point in a function.
+
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
+"""
 import numpy as np
 import matplotlib.pyplot as plt
 
@@ -27,7 +32,7 @@ def select(pop, fitness):    # nature selection wrt pop's fitness
 
 
 def crossover(parent, pop_copy):     # mating process (genes crossover)
-    if np.random.uniform(0, 1) < CROSS_RATE:
+    if np.random.rand() < CROSS_RATE:
         i_ = np.random.choice(np.arange(POP_SIZE), size=1, replace=False)  # select another individual from pop
         cross_points = np.random.randint(0, 2, DNA_SIZE).astype(np.bool)  # choose a crossover points
         parent[cross_points] = pop[i_, cross_points]  # mating and produce one child
@@ -36,7 +41,7 @@ def crossover(parent, pop_copy):     # mating process (genes crossover)
 
 def mutate(child):
     for point in range(DNA_SIZE):
-        if np.random.uniform(0, 1) < MUTATION_RATE:
+        if np.random.rand() < MUTATION_RATE:
             child[point] = 1 if child[point] == 0 else 0
     return child
 

tutorial-contents/Genetic Algorithm/Match Phrase.py

@@ -1,3 +1,8 @@
+"""
+Visualize Genetic Algorithm to match the target phrase.
+
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
+"""
 import numpy as np
 
 TARGET_PHRASE = 'You get it!'       # target DNA

tutorial-contents/Genetic Algorithm/Microbial Genetic Algorithm.py

@@ -1,3 +1,8 @@
+"""
+Visualize Microbial Genetic Algorithm to find the maximum point in a graph.
+
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
+"""
 import numpy as np
 import matplotlib.pyplot as plt
 

tutorial-contents/Genetic Algorithm/Travel Sales Person.py

@@ -1,3 +1,8 @@
+"""
+Visualize Genetic Algorithm to find the shortest path for travel sales problem.
+
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
+"""
 import matplotlib.pyplot as plt
 import numpy as np
 
@@ -38,7 +43,7 @@ def select(self, fitness):
         return self.pop[idx]
 
     def crossover(self, parent, pop):
-        if np.random.uniform(0, 1) < self.cross_rate:
+        if np.random.rand() < self.cross_rate:
             i_ = np.random.choice(np.arange(self.pop_size), size=1, replace=False)  # select another individual from pop
             cross_points = np.random.randint(0, 2, self.DNA_size).astype(np.bool)  # choose crossover points
             keep_city = parent[~cross_points]  # find the city number
@@ -48,7 +53,7 @@ def crossover(self, parent, pop):
 
     def mutate(self, child):
         for point in range(self.DNA_size):
-            if np.random.uniform(0, 1) < self.mutate_rate:
+            if np.random.rand() < self.mutate_rate:
                 swap_point = np.random.randint(0, self.DNA_size)
                 swapA, swapB = child[point], child[swap_point]
                 child[point], child[swap_point] = swapB, swapA

tutorial-contents/Using Neural Nets/NEAT/run_xor.py

@@ -1,5 +1,8 @@
 """
-2-input XOR example -- this is most likely the simplest possible example.
+Using NEAT for supervised learning. This example comes from http://neat-python.readthedocs.io/en/latest/xor_example.html
+
+The detail for NEAT can be find in : http://nn.cs.utexas.edu/downloads/papers/stanley.cec02.pdf
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
 """
 
 import os

tutorial-contents/Using Neural Nets/NEAT_gym/run_cartpole.py

@@ -1,3 +1,9 @@
+"""
+Using NEAT for reinforcement learning.
+
+The detail for NEAT can be find in : http://nn.cs.utexas.edu/downloads/papers/stanley.cec02.pdf
+Visit my tutorial website for more: https://morvanzhou.github.io/tutorials/
+"""
 import neat
 import numpy as np
 import gym