Artificial Intelligence for Simple Games

Course Curriculum

Chapter 1: Installation

Lecture 1: Installing Anaconda

Chapter 2: Get the materials

Lecture 1: Get the materials

Lecture 2: EXTRA: Learning Path

Chapter 3: Genetic Algorithms Intuition

Lecture 1: Plan of Attack

Lecture 2: The DNA

Lecture 3: The Fitness Function

Lecture 4: The Population

Lecture 5: The Selection

Lecture 6: The Crossover

Lecture 7: The Mutation

Chapter 4: Genetic Algorithms Practical

Lecture 1: Step 1 – The Introduction

Lecture 2: Step 2 – Importing the libraries

Lecture 3: Step 3 – Creating the bots

Lecture 4: Step 4 – Initializing the random DNA

Lecture 5: Step 5 – Building the Crossover method

Lecture 6: Step 6 – Random Partial Mutations 1

Lecture 7: Step 7 – Random Partial Mutations 2

Lecture 8: Step 8 – Initializing the main code

Lecture 9: Step 9 – Creating the first population

Lecture 10: Step 10 – Starting the main loop

Lecture 11: Step 11 – Evaluating the population

Lecture 12: Step 12 – Sorting the population

Lecture 13: Step 13 – Adding best previous bots to the population

Lecture 14: Step 14 – Filling in the rest of the population

Lecture 15: Step 15 – Displaying the results

Lecture 16: Step 16 – Running the code

Chapter 5: Q-Learning

Lecture 1: Q-Learning Intuition: Plan of Attack

Lecture 2: Q-Learning Intuition: What is Reinforcement Learning?

Lecture 3: Q-Learning Intuition: The Bellman Equation

Lecture 4: Q-Learning Intuition: The Plan

Lecture 5: Q-Learning Intuition: Markov Decision Process

Lecture 6: Q-Learning Intuition: Policy vs Plan

Lecture 7: Q-Learning Intuition: Living Penalty

Lecture 8: Q-Learning Intuition: Q-Learning Intuition

Lecture 9: Q-Learning Intuition: Temporal Difference

Lecture 10: Q-Learning Intuition: Q-Learning Visualization

Chapter 6: Q-Learning Practical

Lecture 1: Step 1 – Introduction

Lecture 2: Step 2 – Importing the libraries

Lecture 3: Step 3 – Defining the parameters

Lecture 4: Step 4 – Environment and Q-Table initialization

Lecture 5: Step 5 – Preparing the Q-Learning process 1

Lecture 6: Step 6 – Preparing the Q-Learning process 2

Lecture 7: Step 7 – Starting the Q-Learning process

Lecture 8: Step 8 – Getting all playable actions

Lecture 9: Step 9 – Playing a random action

Lecture 10: Step 10 – Updating the Q-Value

Lecture 11: Step 11 – Displaying the results

Lecture 12: Step 12 – Running the code

Chapter 7: Deep Q-Learning with ANNs

Lecture 1: Deep Q-Learning Intuition: Plan of Attack

Lecture 2: Deep Q-Learning Intuition: Step 1

Lecture 3: Deep Q-Learning Intuition: Step 2

Lecture 4: Deep Q-Learning Intuition: Experience Replay

Lecture 5: Deep Q-Learning Intuition: Action Selection Policies

Chapter 8: Deep Q-Learning Practical

Lecture 1: Step 1 – Introduction

Lecture 2: Step 2 – Brain – Importing the libraries

Lecture 3: Step 3 – Brain – Building the Brain class

Lecture 4: Step 4 – Brain – Creating the Neural Network

Lecture 5: Step 5 – DQN Memory – Initializing the Experience Replay Memory

Lecture 6: Step 6 – DQN Memory – Remembering new experience

Lecture 7: Step 7 – DQN Memory – Getting the batches of inputs and targets

Lecture 8: Step 8 – DQN Memory – Initializing the inputs and the targets

Lecture 9: Step 9 – DQN Memory – Extracting transitions from random experiences

Lecture 10: Step 10 – DQN Memory – Updating the inputs and the targets

Lecture 11: Step 11 – Training – Importing the libraries

Lecture 12: Step 12 – Training – Setting the parameters

Lecture 13: Step 13 – Training – Initializing the environment, the brain and dqn

Lecture 14: Step 14 – Training – Starting the main loop

Lecture 15: Step 15 – Training – Starting to play the game

Lecture 16: Step 16 – Training – Taking an action

Lecture 17: Step 17 – Training – Updating the Environment

Lecture 18: Step 18 – Training – Adding new experience, training the AI, updating cur. state

Lecture 19: Step 19 – Training – Lowering epsilon and displaying the results

Lecture 20: Step 20 – Running the code

Chapter 9: Deep Convolutional Q-Learning

Lecture 1: Deep Convolutional Q-Learning Intuition: Plan of Attack

Lecture 2: Deep Convolutional Q-Learning Intuition: Deep Convolutional Q-Learning Intuition

Lecture 3: Deep Convolutional Q-Learning Intuition: Eligibility Trace

Chapter 10: Deep Convolutional Q-Learning Practical

Lecture 1: Step 1 – Introduction

Lecture 2: Step 2 – Brain – Importing the libraries

Lecture 3: Step 3 – Brain – Starting building the Brain class

Lecture 4: Step 4 – Brain – Creating the neural network

Lecture 5: Step 5 – Brain – Building a method that will load a model

Lecture 6: Step 6 – DQN – Building the Experience Replay Memory

Lecture 7: Step 7 – Training – Importing the libraries

Lecture 8: Step 8 – Training – Defining the parameters

Lecture 9: Step 9 – Training – Initializing the Environment the Brain and the DQN

Lecture 10: Step 10 – Training – Building a function to reset the current state

Lecture 11: Step 11 – Training – Starting the main loop

Lecture 12: Step 12 – Training – Resetting the Environment and starting to play the game

Lecture 13: Step 13 – Training – Selecting an action to play

Lecture 14: Step 14 – Training – Updating the environment