Implementing AI to Play Games [Video]

Implementing AI to Play Games [Video]

image description

Course Description

Harness the power of AI to solve and play powerful and smarter puzzles and games by itself and against humans! In video games, Artificial Intelligence is used to generate responsive or intelligent behavior primarily in Non-Player Characters (NPCs), like human intelligence. In this course, we look at games; we understand how to decide which move to take based on future possibilities and payoffs (just as, in chess, we look n-moves ahead into the future). We explore how to solve applications where there are a number of parameters to optimize, such as time or distance, and the possibilities are exponential. We look at how to design the various stage of the evolutionary algorithm that will control performance. We take a sample game—Tic-Tac-Toe—and show how various steps of the algorithm are implemented in code. And we look at color filling as a constraint satisfaction application and see how various algorithm concepts are applied in code. Finally, we also explain a trip-planning

application and see how the application is solved through evolutionary algorithms. Style and Approach A fun course packed with step-by-step instructions, working examples, and helpful advice. You will learn how AI is used to make your games smarter. This comprehensive course is divided into clear bite-size chunks so you can learn at your own pace and focus on the areas of most interest to you.

What you will learn

Perform searches in games Implement a game evaluation function in your game Quantize the desirability of a move for your game Explore a game tree using AI Work on how to optimize a search Design an evolutionary algorithm Implement various stages of the evolutionary algorithm Improve the performance of evolutionary algorithms by adding visualizations How to solve a search which has certain constraints for the variables

Curriculum

Section 1: Constraint Satisfaction Problem

Section 2: Using AI to Play Games

Section 3: Evolutionary Search