Game AI versus AI: An Introduction to AI Game Programming - PowerPoint Presentation

Slide1

Game AI versus AI: An Introduction to AI Game Programming

Héctor Muñoz-Avila

Slide2

Some Interesting Facts About the Game Industry

As of 2004, the game industry is at least as large (measured in terms of revenue) as the movie (Hollywood) industry

As of 2007, the video game sector remains one of the above-average growth segments of the U.S. and global entertainment industries

Video game sales remains strong today. As an example, sales of the latest World of Warcraft expansion (November/2010) outpaced previous expansions

Slide3

AI vs

Game AI

We need to

understand the connections and the misconceptions from both sides

AI

research

A

C

B

A

B

C

A

C

B

C

B

A

B

A

C

B

A

C

B

C

A

C

A

B

A

C

B

B

C

A

A

B

C

A

B

C

A

B

C

Game AI

as game practitioners implemented it

Slide4

Game AI

Do you know what is attack Kung-Fu style?

http://

www.youtube.com/watch?v=q1yId7Ug2Mg

Slide5

Half-Life: Gordon Freeman’s First Encounter with the Marines

Do they attack Kung-Fu style?

Slide6

Half-Life Kung-Fu Attack

http://

www.youtube.com/watch?v=dKNGRuXVa4U

Actually no more than 2 marines are attacking at any time

The other marines take cover, move around etc.

When one of the attacking marines run out of ammo, is wounded, dies, etc., one of the others take his place

Some reactions are hard-coded and scenario-dependent

Slide7

Game AI

Term refers to the algorithms controlling:

The computer-controlled units/opponents

Gaming conditions (e.g., weather)

Path finding

Attack Kung-Fu style is an example of game AI for the computer opponent

Programming intentional mistakes is also part of controlling the computer opponent “AI”

Slide8

Programming “Good” AI Opponent

(according to Lars Liden; Ch. 2; AIWS1)

Enemies move before firing

Make mob/enemy visible

Announce enemy presence by sound or other means

http://www.youtube.com/watch?v=vL8YfqyU4Fo&feature=related

Slide9

Programming “Good” AI Opponent (II)

(according to Lars Liden; Ch. 2)

Have horrible aim (rather than doing less damage)

Miss the first time

Warn the player (e.g., music, sound)

Kung-Fu attacks

Slide10

Some AI Topics

Search

Planning

Game theory

Machine

learning

Case-based reasoning

RoboticsComputer vision

Neural networks

Some of which have been applied in commercial computer games

Slide11

Using

AI

in Games

(1)

Path finding for

our units

using

heuristic search

(1)

Deliberative Planning of objectives with

automated planning

What-if analysis to counter the

opponent

using

game theory

(2)

Our units

avoid repeating mistakes by using

machine learning

and

case-based reasoning

(3)

(2)

(3)

Slide12

Memory Capacity

Slide13

The Power of Game Computing and Its Consequences

Every year, computers are made with more and more memory

This makes for bigger and bigger maps in games

Much effort must be spent on pathfinding which could be better utilized elsewhere

The amount of memory gained goes into the bigger maps and unfortunately a lot of it must be spent on navigation

Slide14

Pathfinding

Frequently games use a collection of nodes (“waypoints”) and edges connecting those nodes

Algorithms are devised that find a

path

through the waypoints for two given nodes

Challenges arise when there are too many waypoints

Divide and Conquer the map

Slide15

Area Based Path Look Up Tables: A Hierarchical Example

Slide16

Game Theory

Idea

: Build a tree describing all possible gaming moves between two opponents

Analyze tree looking ahead N moves into the “horizon” and select best move

Well understood: Nash equilibrium

Challenge

: game tree can be too large

Parallelism & heuristics: Deep Blue

Abstract states: Poki-Poker

Restrictions

: perfect information and deterministic outcomes

Slide17

Cutting Off Search

When to cutoff minimax expansion?

Potential problem with cutting off search:

Horizon problem

Solution:

Fixed depth limit

Iterative deepening until times runs out

Decision made by opponent is damaging but cannot be “seen” because of cutoff

Quiescent: states that are unlikely to exhibit wild swings in the values of the evaluation functions

Slide18

Evaluation Function

Evaluation Function

Is an

estimate

of the actual utility

Typically represented as a linear function:

EF(state) = w1

f1(state) + w2f2(state) + … + wnfn(state) Example:

Chess

weight: Piece

 Number(w1) Pawn

 1 (w2

) Knight  3

(w3) Bishop  3

(w4) Rook  5

(w5) Queen  9

Function; state

 Number

f1

= #(pawns,w)  #(pawns,b)f

2 = #(knight,w)  #(knight,b)

f3 = #(bishop,w)  #(bishop,b)

f4 = #(rook,w) 

#(rook,b)f5 = #(knight,w)

 #(knight,b)

Slide19

Example: Horizon Problem

“all things been equal”

White moves,

Who is winning?

Is this consistent with Evaluation function?

Black

No!

Slide20

Machine Learning: An Example

A number of fixed

domination

locations.

When a team member steps into one of these locations, the status of the location changes to be under the control of his/her team.

The team gets a point for every five seconds that each domination location remains under the control of that team.

The game is won by the first team that gets a pre-specified amount of points.

We used

Unreal Tournament

©

a team-based FPS

Slide21

The RETALIATE Algorithm

Uses Reinforcement Learning:

Agents learn behavior policies through rewards and punishments

Policy - Determines what action to take from a given state

Agent’s goal is to maximize some reward

Can be shown to converge to optimal policy (sort of equilibrium)

Slide22

Before/After Policies

Before

After

Slide23

AI in Commercial Games

Automated

Planning

Machine

Learning

Reasoning with Uncertainty

Slide24

Interested?

CSE 348 AI Game Programming

CSE 42 Principles of Computer Game Design

CSE 327 AI Theory and Practice

Research:

Independent Studies (undergraduates): 30+

MS Thesis: 10

PhD Dissertations: 5