What You See Is Not What You Get

For many, even in the game development community, the goal of AI development is to make the "winningest" AI that one can from the perspective of the developer, which sounds like a reasonable goal. A group of players played a turn-based strategy game against two dozen AI opponents; ranked t...

Full description

Saved in:
Bibliographic Details
Published inGame AI Pro 3 pp. 31 - 47
Main Authors Wetzel, Baylor, Anderson, Kyle
Format Book Chapter
LanguageEnglish
Published CRC Press 2017
Edition1
Subjects
AI’s Action
Chaos Monsters
Black Dragon
Attack Score
Velocity Obstacle
Turn Based Strategy Game
Player’s Perception
Good Ai
Simple Ai
AI Development
Vice Versa
Random Number Generator
Markov Chain Monte Carlo Simulations
Ai Opponent
Game AI
AI’s Complexity
Boss Battles
Weak Units
Ai Technique
Ai Designer
Monte Carlo Algorithm
Bone Dragon
Blatant Cheating
AI Agent
Online AccessGet full text
ISBN9781498742580
1498742580
DOI10.4324/9781315151700-4

Cover

More Information
Summary:For many, even in the game development community, the goal of AI development is to make the "winningest" AI that one can from the perspective of the developer, which sounds like a reasonable goal. A group of players played a turn-based strategy game against two dozen AI opponents; ranked them on difficulty, realism, and fun; and explained what they believed each AI's strategy was. Complex techniques often achieved higher scores but seemed no more difficult, realistic, or fun to players than significantly simpler AIs. No factor correlated highly with how much players enjoyed playing a particular opponent. The AI considered the most realistic was a Monte-Carlo-based algorithm that was arguably the least human-like AI in the test. Use of available information, use of direct versus summary information, technique complexity, predictability, strategy obviousness, persistency, revenge, and hustling are eight properties of an AI opponent.
ISBN:9781498742580
1498742580
DOI:10.4324/9781315151700-4