Measuring Entertainment and Automatic Generation of Entertaining Games

hostitchAI and Robotics

Oct 23, 2013 (3 years and 10 months ago)

104 views

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Measuring Entertainment and Automatic Generation of
Entertaining Games

PhD Thesis Defense

Zahid Halim

Date:
23
rd

November
2010

http://ming.org.pk/zahid.htm

Supervised By: Dr.
Rauf Baig

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Presentation Outline



Introduction


Problem Statement


Thesis Objective


Contribution


Proposed Metrics


Board Based Games


Predator/prey Games


Conclusion


Future Plans


Major Achievements


Questions


Bibliography

2

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Problem Statement



Abundance of Games



Game Development Process



Issues


Quantifying entertainment


Writing new games/versions


3

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Thesis Objective



Define entertainment in games



Develop a quantitative measure of entertainment



Computational Intelligence to generate entertaining games



Verify evolved game’s entertainment


4

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Entertainment Metrics


Board Based Games



Duration of the Game



Intelligence for Playing the Game



Dynamism Exhibited by the Pieces



Usability of the Play Area


5

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Duration of the Game Metrics



6



Calculated by playing the game n times


Taking average number of moves over these n games


Maximum moves are fixed at 100

Raw val ue of D

0
0.2
0.4
0.6
0.8
1
1.2
1
5
9
13
17
21
25
29
33
37
41
45
49
53
57
61
65
69
73
77
81
85
89
93
97
101
Scaled value of D

Durati on of game (D)

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Intelligence for Playing the Game Metrics



Number of wins of an intelligent controller over one making
random moves


Higher number of wins against the random controller means that
the game requires intelligence to be played and does not have too
many frustrating dead ends


I
K
is
1
if intelligent controller wins the game otherwise it is
0

7

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Dynamism Exhibited by the Pieces Metrics



Game whose rules encourage greater dynamism of movement in its
pieces would be more entertaining


8

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Usability of the Play Area Metrics



It is interesting to have the play area maximally utilized during the
game


9

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Combined fitness



All chromosomes evaluated separately according to each of the four
metrics



Then the population is sorted on each of the metrics separately



A rank based fitness is assigned to each chromosome.



The best chromosome assigned the highest fitness



Ranks multiplied by weights


10

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Entertainment Metrics


Predator/prey Games



Duration of the Game



Appropriate Level of Challenge



Diversity



Usability

11

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Duration of the Game Metrics



In

order

to

evolve

games

of

short

to

medium

duration

we

have

fixed

the

upper

bound

of

steps

to

100


3

to

5

minute

game

if

played

with

arrow

keys


Premature

death

of

agent

possible


The

death

possibility

of

the

agent

should

not

be

very

high



Case

the

resulting

games

short

and

frustrating



Depend

upon

the

agent

playing

the

game

12

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Appropriate Level of Challenge

Metrics



High score, achieved easily and similarly too low


Not challenging enough



Game rules should provide an appropriate level of challenge



Factor of uncertainty in the rules of the game

13

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Diversity Metrics



The diversity of the game is based upon the diversity of the pieces
in the game



The behavior of the moving pieces of the game should be
sufficiently diverse so that it cannot be easily predicted

14

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Usability Metrics



It is interesting to have the play area maximally utilized during the
game



If most of the moving pieces remain in a certain region of the play
area then the resulting game may seem strange

15

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Combined fitness



All chromosomes evaluated separately according to each of the four
metrics



Then the population is sorted on each of the metrics separately



A rank based fitness is assigned to each chromosome



The best chromosome assigned the highest fitness



Ranks multiplied by weights


16

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Board Based Games

Search Space

Search Space Dimension

Possible Values

Select Values

Checkers

Chess

Play Area

Only black squares are used

Both white & black squares
are used

Both white & black squares are used

Types of Pieces

Initially 1, maximum 2

6

6

Number of pieces/type

12, variable (but max. 12)

16

variable but at maximum 24

Initial position

Black squares of first 3 rows

Both white & black squares
of first 2 rows

Both white & black squares of first 3
rows

Movement direction

Diagonal forward and
Diagonal, forward backward

All directions, straight
forward, straight forward
and backward, L shaped,
diagonal forward

All directions, straight forward, straight
forward and backward, L shaped,
diagonal forward

Step Size

One Step

One Step, Multiple Steps

One Step, Multiple Steps

Capturing Logic

Step over

Step into

Step over, step into

Game ending logic

No moves possible for a
player

No moves possible for the
king

No moves possible for a player, no
moves possible for the king

Conversion Logic

Checkers into king

Soldiers into queen or any
piece of choice

Depends upon rules of the game

Mandatory to capture

Yes

No

Depends upon rules of the game

Turn passing allowed

No

No

No

17

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Chromosome Encoding

Gene

Title

Value

1

Placement of gene of each type

0
-
6

:

24

25

Movement logic of each type

1
-
6

:

30

31
-
36

Step Size

0/1

37

Capturing logic move into cell or jump over 0/1

0/1

:

42

43

Piece of honour

0
-
6

44

Conversion Logic 0
-
6

0
-
6

:

49

50

Mandatory to capture or not

0/1

18

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Random Controller

19

1.
Input
:

Game

Board

current

state


2.

Generate

all

legal

moves

3.

Store

the

moves

in

a

queue

4.

Shuffle

the

queue

5.

If not mandatory to kill

6.


Randomly select a move from the queue.

7.

Else

8.



Select a move that captures an opponent's piece, if such move exists

9.



Otherwise, randomly select a move from the queue.

10.
Output: Next move to take

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Min
-
Max based Controller

20

1.
Input: Game Board current state

1.
For each piece

2.

priority=0

3.
For each piece

4.

if is piece of honor

5.

priority = priority +1 000

6.

if movement logic all directions

7.

priority = priority + 8

8.

if movement logic diagonal Forward and Backward

9.

priority = priority + 7

10.

if movement logic Straight Forward and Backward

11.

priority = priority + 7

12.

if movement logic diagonal Forward

13.

priority = priority + 6

14.

if movement logic Straight Forward

15.

priority = priority + 6

16.

if movement logic L shaped

17.

priority = priority + 5

18.

if capturing logic step into

19.

priority = priority + 4

20.

if capturing logic step over

21.

priority = priority + 3

22.
Count the number of pieces of Player A

23.
Multiply the number of pieces of a type with its relevant priority

24.
Count the number of pieces of Player B

25.
Multiply the number of pieces of a type with its relevant priority

26.
Calculate boardValue = WeightSumofA
-
WeightSumofB

27.
Check if the Piece of Honour is dead add
-
1000 to boardValue

28.
Check if the Piece of Honour is NOT dead add +1000 to
boardValue

29.
Output: boardValue



FAST
-
National University of Computer and Emerging Sciences, Islamabad

Experimentation Setup



1
+
1
Evolutionary Strategy (ES)


10
chromosomes are randomly initialized


The evolutionary algorithm is run for
100
iterations


Mutation only with probability of
30
percent


One parent produce one child


Fitness difference is calculated


If it is greater than
4
(at least half times better) child is
promoted to the next population

21

FAST
-
National University of Computer and Emerging Sciences, Islamabad

22

0.00
5.00
10.00
15.00
20.00
25.00
30.00
1
4
7
10
13
16
19
22
25
28
31
34
37
40
43
46
49
52
55
58
61
64
67
70
73
76
79
82
85
88
91
94
97
100
Duration
Intelligence
Dynamism
Usability
Metrics values of one family

FAST
-
National University of Computer and Emerging Sciences, Islamabad

23

Piece
No

Movement Logic

Step Size

Capturing
Logic

Conversion
Logic



1

L

Multiple

Step Into

6

2

Diagonal Forward &
Backward

Single

Step Over

5

3

All Directions

Multiple

Step Into

Nil

4

Straight Forward

Multiple

Step Into

1

5

Straight Forward

Multiple

Step Over

2

6

All Directions

Multiple

Step Over

3













Piece of Honour

5





Mandatory to Capture

No



Game Rules/Pieces Positions

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Learnability of Evolved Games
1
/
2



Schmidhuber’s theory of artificial curiosity


Chellapilla’s architecture of the controller for checkers player


5
layers in the ANN


Input with
64
neurons


First hidden layer with
91
neurons


Second hidden layer with
40
neurons


Third with
10
neurons


Output layer with
1
neuron.


Hyperbolic tangent function is used in each neuron


Connection weights range is [
-
2
,
2
]


24

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Learnability of Evolved Games 2/2



The

training

of

the

ANN

is

done

using

co
-
evolution


GA

population

is

initialized

representing

weight


Each

individual

played

against

randomly

selected

5

others


Mutation

only

25

Game 1
Game 2
Game 3
Game 4
Learnability
98
92
104
30
0
20
40
60
80
100
120
Iteration to achieve maximum fitness

Learnability

FAST
-
National University of Computer and Emerging Sciences, Islamabad

User Survey



Human user survey on 10 subjects


Chosen such that they have at least some level of interest towards
computer games

26

1
2
3
4
Liked (%)
80
70
90
10
0
10
20
30
40
50
60
70
80
90
100
Game Liked (%)

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Predator/prey Games

Search Space



14 X 14 grid excluding the boundary
walls.


Couple of walls at fixed positions and of
size 7 cells



There is one player controlled by the
human player.


There are N (0
-
20)other pieces of M (1,2
and 3) types


Maximum duration 100 game steps


Finish game


Agent dies


Maximum score is achieved


Maximum game steps utilized



Movement logic



No movement


Clockwise


Counter clockwise


Random


Random direction



Collision logic


no effect


random relocation to a new location
on the grid


death



Scoring logic


+1,
-
1, 0

27

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Chromosome Encoding

Number of predators

Red

0
-
20

Collision logic

Blue
-
Green

0
-
2

Green

0
-
20

Blue
-
Blue

0
-
2

Blue

0
-
20

Blue
-
Agent

0
-
2

Movement logic

Red

0
-
4

Agent
-
Red

0
-
2

Green

0
-
4

Agent
-
Green

0
-
2

Blue

0
-
4

Agent
-
Blue

0
-
2

Collision logic

Red
-

Red

0
-
2

Score logic

Red
-

Red

-
1,0,+1

Red
-

Green

0
-
2

Green
-
Green

-
1,0,+1

Red
-
Blue

0
-
2

Blue
-
Blue

-
1,0,+1

Red
-

Agent

0
-
2

Agent
-
Red

-
1,0,+1

Green
-
Red

0
-
2

Agent Green

-
1,0,+1

Green
-
Green

0
-
2

Agent
-
Blue

-
1,0,+1

Green
-
Blue

0
-
2

Green
-
Red

-
1,0,+1

Green
-
Agent

0
-
2

Blue
-
Red

-
1,0,+1

Blue
-
Red

0
-
2

Blue
-
Green

-
1,0,+1

28

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Rule Based Controller



The

controller

notes

the

nearest

piece

(if

any)

in

each

of

the

four

directions

moves

one

step

towards

the

nearest

score

increasing

piece




If

there

are

no

score

increasing

piece,

step

according

to

priority

list



Move

in

the

empty

direction


If

more

than

one

such

directions

move

towards

farthest



Move

towards

score

neutral

piece



Move

towards

score

decreasing

piece



Move

towards

death

causing

piece


29

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Neural Network Based Controller



Multi
-
layer fully feed forward


6 neurons in the input layer



5 neurons in the hidden layer


4 output layer neurons


Sigmoid activation function


Edges weights
-
5 to +5

30


xr


xg


xb


yg



yb


yr

N
u

N
d

N
l

N
r

C
o
n
n
e
c
ti
o
n
E
d
g
e
s


C
o
n
n
e
c
ti
o
n
E
d
g
e
s


C
o
n
n
e
c
ti
o
n
E
d
g
e
s


FAST
-
National University of Computer and Emerging Sciences, Islamabad

Experimentation Setup



10 chromosomes are randomly initialized by the GA



One offspring is created for each chromosome


Duplicating it


Mutating any one of its gene



Results in 20 chromosomes from which 10 best chosen



100 generations

31

FAST
-
National University of Computer and Emerging Sciences, Islamabad

32

Appropriate level of challenge

Duration of game

Diversity

Usability

Combined Fitness

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Controller Learning Ability

33

0
200
400
600
800
1000
1200
Diversity-RB
Duration-RB
Challenge-RB
Usability-RB
Diversity-ANN
Duration-ANN
Challenge-ANN
Usability-ANN
Combined-RB
Combined-ANN
Random
Diversity-
RB
Duration-
RB
Challenge-
RB
Usability-
RB
Diversity-
ANN
Duration-
ANN
Challenge-
ANN
Usability-
ANN
Combined-
RB
Combined-
ANN
Random
No. Of Iterations
3
5
6
1000
71
1000
1000
64
320
310
63
FAST
-
National University of Computer and Emerging Sciences, Islamabad

User Survey



10
subjects


Conducted in two different sets on different days


Rule based controller


ANN based controller


Each individual was given
6
games


Play
2
times

34

0
2
4
6
8
10
12
Rule Based Controller
ANN Based Controller
Random

0%

Durati on

4%

Chal l enge

32%

Di versi ty

0%

Usabi l ity

24
%

Combi ne
d Fi tness

40%

Human User Survey

ANN Based Controller

Random

0%

Durati on

12%

Chal l enge

23%

Di versi ty

0%

Usabi l ity

18%

Combi ned
Fi tness

47
%

Human User Survey

Rule Based Controller

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Conclusion



Identified the entertainment factors



Introduced entertainment metrics


Board based genre of games


Video games


Predator/prey



Entertainment factors dependent on genre


Automatic generation of entertaining games


Verification


Learnability of Evolved Games


User survey



35

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Limitations



Appropriate for offline mode



Processor intensive


Multiple times


36

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Future Plans



Multi objective genetic algorithm



Model the behavior of a particular human player


Evolving content for games against his/her playing patterns



Physical activating games for medical science


37

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Measuring Entertainment and Automatic Generation of
Entertaining Games

Thank you for your
patience

Questions

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Bibliography
1
/
7


J
.
Schmi dhuber
,

”Devel opmental

robotics,

opti mal

arti fi cial

curi osi ty,

creati vi ty,

musi c,

and

the

fi ne

arts”,

Connecti on

Sci ence,

vol
.

18
,

pp
.
173

187
,

2006



N
.

Esposi to,

“A

Short

and

Si mpl e

Defi ni ti on

of

What

a

Vi deogame

Is”,

i n

proceedi ngs

of

Di gi tal

Games

Research

Associati on

(
Di GRA
),

Vancouver,

Canada,

16
-
20

June,

2005



J
.
Smed

and

H
.
Hakonen
,

"Towards

a

Defi ni ti on

of

a

Computer

Game",

Techni cal

Report,

Computer

Games

Research

Group,

Department

of

Informati on

Technol ogy,

Uni versi ty

of

Turku,

Fi nl and,

2005



S
.

Lucas,”

Evol vi ng

a

neural

network

l ocati on

eval uator

to

pl ay

Ms
.

Pac
-
Man
.

In

Graham

Kendall

and

Si mon

Lucas,

edi tors”,

Proceedi ngs

of

the

IEEE

Symposi um

on

Computati onal

Intel l i gence

and

Games,

pages

203

210
,

Essex

Uni versi ty,

Col chester,

UK,

4

6

Apri l

2005



E
.

Norl i g

and

L
.

Sonenberg
,



An

approach

to

eval uati ng

human

characteri sti cs

i n

agents”,

In

Gabri el a

Li ndemann
,

Dani el

Mol dt
,

Mari o

Paol ucci
,

and

Bi n

Yu,

edi tors,

i n

proceedi ngs

of

the

Internati onal

Workshop

on

Regul ated

Agent
-
Based

Systems
:

Theori es

and

Appli cati ons

,

Bol ogna,

Ital y,

16
th

Jul y

2002



K
.

O
.

Stanl ey,

N
.

Kohl,

R
.

Sherony
,

and

R
.

Mii kkulai nen
,”

Neuroevol uti on

of

an

automobil e

crash

warni ng

system”,

i n

proceedi ngs

of

the

Geneti c

and

Evol uti onary

Computati on

Conference

,

Washi ngton

DC,

USA,

25
-
29

June,

2005



D
.

A
.

Ji renhed
,

G
.

Hessl ow
,

and

T
.
Zi emke
,

“Expl ori ng

i nternal

si mulati on

of

percepti on

i n

mobil e

robots”,

i n

proceedi ngs

of

the

Fourth

European

Workshop

on

Advanced

Mobi l e

Robots,

Lund,

Sweden,

19
-
21

September,

2001



C
.

Schl i eder
,

P
.

Ki efer,

S
.

Matyas
,”

Geogames
:

Desi gni ng

Locati on
-
Based

Games

from

Cl assi c

Board

Games”,

IEEE

Intel li gent

Systems

21
(
5
)
:

40
-
46
,

2006



H
.

Lund,

T
.

Kl i tbo

and

C
.

Jessen
,

"
Pl ayware

Technol ogy

for

Physi cally

Acti vating

Pl ay",

Arti fi cial

Li fe

and

Roboti cs

Journal,

165
-
174
,

2005



L
.

Davi s,

“Hybri di zati on

and

Numeri cal

Representati on”,

i n

L

Davi s

(
ed
),

The

Handbook

of

Geneti c

Al gori thms,

Van

Nostrand

Rei nhol d,

1991
,

pp

61

71


39

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Bibliography 2/7


I
.
Wi tten
,

and

E
.
Frank
,

“Data

Mi ni ng
:

Practi cal

Machine

Learni ng

Tool s

and

Techni ques”,

2
nd

Edi ti on,

Morgan

Kaufman,

San

Franci sco,

CA,

2004



I
.

Rechenberg
,


Evol uti onsstrategi e
:

Opti mi erung

technischer

Systeme

nach

Pri nzi pi en

der

Bi ol ogischen

Evol uti on”,

Frammann
-
Hol zboog

Verl ag
,

Stuttgart,

1973



K
.

Chel l apilla
,

D
.

B
.

Fogel
,

”Evol vi ng

an

expert

checkers

pl ayi ng

program

wi thout

usi ng

human

experti se”,

IEEE

Trans
.

Evol uti onary

Computati on

5
(
4
)
:

422
-
428
,

2001



P
.

J
.

Angel i ne
,

G
.

M
.

Sauders
,

and

J
.

B
.

Pollack,



An

evol uti onary

al gori thm

that

constructs

recurrent

neural

networks”,

IEEE

Transacti on

on

Neural

Networks,

5
:
54

65
,

1994



T
.

Back

and

H
.

P
.

Schwefel
,

“An

overvi ew

of

evol uti onary

al gorithms

for

paramater

opti mi zati on”,

Evol uti onary

Computati on,

1
(
1
)
:
1

23
,

1993



H
.

Ii da,

N
.

Takeshi ta
,

and

J
.

Yoshi mura,

“A

Metri c

for

Entertai nment

of

Board

Games
:

Its

Applicati on

for

Evol uti on

of

Chess

Vari ants”,

In

Nakatsu
,

R
.
,

and

Hoshi no,

J
.
,

eds
.
,

Entertai nment

Computi ng
:

Technol ogi es

and

Appli cati ons

(Proceedi ngs

of

IWEC

2002
),

pages

65
-
72
.

Boston,

MA
:

Kl uwer

Academi c

Publ i shers,

2003



A
.

Ci ncotti

and

H
.

Ii da,

“Outcome

Uncertai nty

And

Interestedness

In

Game
-
Playi ng
:

A

Case

Study

Usi ng

Synchroni zed

Hex”,

In

New

Mathemati cs

and

Natural

Computati on

(NMNC),

vol
.

02
,

i ssue

02
,

pages

173
-
181
,

2006



S
.

Retali s
,

“Creati ng

Adapti ve

e
-
Learni ng

Board

Games

for

School

Setti ngs

Usi ng

the

ELG

Envi ronment”,

Journal

of

Uni versal

Computer

Sci ence
:

2897
-
2908
,

2008



J
.

Togel i us
,

R
.

D
.

Nardi
,

and

S
.

M
.

Lucas,“Towards

automati c

personalised

content

creati on

for

raci ng

games”,

i n

Proceedi ngs

of

the

IEEE

Symposi um

on

Computati onal

Intel l i gence

and

Games,

Pi scataway,

NJ,

1
-
5

Apri l,

2007



S
.

Sevenster
,

A
.
P
.

Engel brecht
,


GARTNet
:

A

Geneti c

Al gori thm

for

Routi ng

i n

Tel ecommuni cati ons

Networks”,

Proceedi ngs

of

CESA
96

IMACS

Mul ticonference

on

Computati onal

Engi neeri ng

i n

Systems

Appli cati ons,

Symposi um

on

Control,

Opti mi zati on

and

Supervisi on,

Lill e,

Prance,

Vol

2
,

1996



40

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Bibliography 3/7


G
.

N
.

Yannakakis

,

J
.

Hall am
,

”Towards

Opti mi zi ng

Entertai nment

In

Computer

Games”,

Appl i ed

Arti fi cial

Intelli gence”,

v
.
21

n
.
10
,

p
.
933
-
971
,

November

2007



M
.

Gal lagher

and

A
.

Ryan,

“Learni ng

to

Pl ay

Pac
-
Man
:

An

Evol uti onary

Rul e
-
based

Approach,”

i n

proceedi ngs

of

IEEE

Congress

on

Evol uti onary

Computati on,

Canberra,

Austral i a,

8
-
12

December
.

2003



G
.

Lankvel d
,

P
.

Spronck
,

M
.

Rauterberg
,

“Di ffi cul ty

Scali ng

through

Incongrui ty”,

i n

proceedi ngs

of

the

Fourth

Arti fi cial

Intelli gence

and

Interacti ve

Di gi tal

Entertai nment

Conference,

Stanford,

Cal i fornia,

22

24

October,

2008



J
.

Togel i us

and

J
.

Schmi dhuber
,

"An

Experi ment

i n

Automati c

Game

Desi gn",

i n

Proceedi ngs

of

IEEE

Computati onal

Intelli gence

and

Games,

Perth,

Austral i a,

15

-

18

December,

2008



J
.

Togel i us
,

S
.

Karakovski y
,

J
.

Koutni k

and

J
.

Schmi dhuber
,

"Super

Mari o

Evol uti on",

i n

proceedi ngs

of

IEEE

Symposi um

on

Computati onal

Intelli gence

and

Games,

Mi l ano,

Ital y,

7
-
10

September,

2009



N
.

Lazzaro
,

“Why

We

Play

Games
:

Four

Keys

to

More

Emoti on

Wi thout

Story”,

i n

proceedi ngs

of

Game

Devel opers

Conference,

San

Jose,

Cali fornia,

8
th

March,

2004



C
.

Pedersen,

J
.

Togel i us
,

and

G
.

N
.

Yannakakis
,

"Opti mi zati on

of

platform

game

l evel s

for

player

experi ence,''

i n

proceedi ngs

of

Arti fi cial

Intelli gence

and

Interacti ve

Di gi tal

Entertai nment

,

Stanford,

Cal i fornia,

14
-
16

October

2009



K
.
Compton

and

M
.

Mateas
,

“Procedural

Level

Desi gn

for

Pl atform

Games”,

i n

proceedi ngs

of

2
nd

Arti fi cial

Intelli gence

and

Interacti ve

Di gi tal

Entertai nment

Conference,

Stanford,

20
-
23

June,

Cal i forni a,

2006



G
.

N
.

Yannakakis

and

J
.

Hallam
,

“Evol vi ng

Opponents

for

Interesti ng

Interacti ve

Computer

Games”,

i n

proceedi ngs

of

the

8
th

Internati onal

Conference

on

the

Si mul ati on

of

Adapti ve

Behavi or,

Los

Angel es,

USA,

13
-
17

Jul y

2004



B
.

D
.

Bryant

and

R
.

Mi i kkulai nen
,

“Acqui ri ng

visi bl y

i ntel li gent

behavi or

wi th

exampl e
-
gui ded

neuroevol uti on
”,

i n

proceedi ngs

of

the

22
nd

nati onal

conference

on

Arti fi ci al

i ntel ligence,

Vancouver,

Bri ti sh

Col umbi a,

Canada,

22
-
26

Jul y,

2007




41

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Bibliography
4
/
7


G
.

N
.

Yannakakis
,

and

J
.

Hall am
,

"Entertai nment

Model i ng

through

Physi ol ogy

i n

Physi cal

Pl ay,"

Internati onal

Journal

of

Human
-
Computer

Studi es,

vol
.

66
,

i ssue

10
,

pp
.

741
-
755
,

October,

2008



R
.

J
.

Orr

and

G
.

D
.

Abowd
,

“The

smart

fl oor
:

a

mechani sm

for

natural

user

i denti fi cati on

and

tracki ng”,

i n

proceedi ngs

of

Conference

on

Human

Factors

i n

Computi ng

Systems,

Netherl ands,

1
-
6

Apri l,

2000



B
.

Ri chardson,

K
.

Leydon
,

M
.

Fernstrom
,

and

J
.

A
.

Paradiso
,

“Z
-
til es
:

Buil di ng

bl ocks

for

modular,

pressure
-
sensi ng

fl oorspaces
”,

i n

proceedi ngs

of

Conference

on

Human

Factors

i n

Computi ng

Systems,

Vi enna,

Austri a,

24
-
29

Apri l,

2004



H
.

H
.

Lund,

T
.

Kl i tbo
,

and

C
.

Jessen
,


Pl ayware

technol ogy

for

physi call y

acti vati ng

pl ay”,

Arti fical

Li fe

and

Robotics

Journal,

vol
.

9
,

no
.

4
,

pp
.

165

174
,

2005



K
.
Grønbæk
,

O
.
S
.
Iversen
,

K
.
J
.
Kortbek
,

K
.
R
.
Ni el sen
,

and

L
.

Aagaard
,

"

i GameFl oor

-

a

Platform

for

Co
-
Located

Collaborati ve

Games",

i n

proceedi ngs

of

the

Internati onal

Conference

on

Advances

i n

Computer

Entertai nment,

Sal zburg,

Austri a,

13
.
-
15
.

June,

2007



N
.

Beume
,

H
.

Dani elsi ek
,

C
.

Ei chhorn
,

B
.

Naujoks
,

M
.

Preuss
,

K
.

Still er,

S
.

Wessi ng
,

“Measuri ng

Fl ow

as

Concept

for

Detecti ng

Game

Fun

i n

the

Pac
-
Man

Game”,

i n

proceedi ngs

of

the

IEEE

Congress

on

Evol uti onary

Computati on,

CEC

2008
,

Hong

Kong,

Chi na,

1
-
6

June,

2008



K
.
O
.
Stanl ey
,

B
.
D
.
Bryant
,

R
.
Mi i kkul ai nen
,

“Evol vi ng

neural

network

agents

i n

the

nero

vi deo

game”,

i n

proceedi ngs

of

IEEE

Symposi um

on

Computati onal

Intel l i gence

and

Games,

Mi l an,

September,

2009



B
.

D
.

Bryant

and

R
.

Mi i kkulai nen
,

"Evol vi ng

stochastic

controll er

networks

for

i ntelli gent

game

agents,"

i n

proceedi ngs

of

IEEE

Congress

on

Evol uti onary

Computati on,

San

Franci sco,

California,

26
-
29

June,

2006



B
.

D
.

Bryant

and

R
.

Mi i kkulai nen
,

“Evol vi ng

visi bl y

i ntelli gent

behavi or

for

embedded

game

agents”,

PhD

thesi s,

Department

of

Computer

Sci ences,

Uni versi ty

of

Texas

at

Austi n,

Austi n,

TX,

2006



D
.
L
.

Roberts,

C
.
R
.

Strong

and

C
.
LIsbell
,”

Esti mati ng

pl ayer

sati sfacti on

through

the

author's

eyes”,

i n

proceedi ngs

of

the

Second

Workshop

on

Opti mi zi ng

Pl ayer

Sati sfacti on,

Cal ifornia,

USA,
6
-
8

Jul y,

2007


42

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Bibliography 5/7


B
.

D
.

Bryant

and

R
.

Mi i kkulai nen
,

”Expl oi ti ng

sensor

symmetri es

i n

exampl e
-
based

trai ni ng

for

i ntelli gent

agents”,

In

Loui s,

S
.

J
.
,

and

Kendall,

G
.
,

eds
.
,

Proceeedi ngs

of

the

IEEE

Symposi um

on

Computati onal

Intel l i gence

and

Games,

Reno

Tahoe,

22
-
24

May,

2006



B
.

D
.

Bryant

and

R
.

Mi i kkulai nen
,


Neuroevol uti on

for

adapti ve

teams,”

i n

proceedi ngs

of

IEEE

Internati onal

Conference

on

El ectroni c

Commerce,

Newport

Beach,

CA,

USA,

24
-
27

June

2003



N
.

Beume
,

T
.

Hei n,

B
.

Naujoks
,

N
.

Pi atkowski
,

M
.

Preuss
,

M
.

and

S
.

Wessi ng
,

“Intel li gent

Anti
-
Groupi ng

i n

Real
-
Ti me

Strategy

Games”,

i n

proceedi ngs

of

IEEE

Symposi um

on

Computati onal

Intel l i gence

and

Games

Perth,

Austral i a,

15

-

18

December,

2008



M
.

Csíkszentmi hál yi
,

“Fl ow
:

The

Psychol ogy

of

Opti mal

Experi ence”,

Harper

and

Row
.

ISBN

0
-
06
-
092043
-
2
,

1991
.


A
.

Bezek
,


Model i ng

Mul tiagent

Games

Usi ng

Acti on

Graphs”,

i n

proceedi ngs

of

Modeli ng

Other

Agents

from

Observati ons,

New

York,

USA,

19
th

Jul y,

2004



B
.

Christian

Bauckhage
,

C
.

Gorman,

Thurau

&

M
.

Humphrys
,

"Learni ng

Human

Behavi or

from

Anal yzi ng

Acti vi ti es

i n

Vi rtual

Environments",

MMI

i nterakti v

journal,

Issue
:

12

Pages
:

3
-
17
,

2007



T
.

Henderson

and

S
.

Bhatti
,

“Model l i ng

user

behavi our

i n

networked

games”,

Mul ti medi a

2001
,

June

2001



H
.

Barber

and

D
.

Kudenko
,

“A

User

Model

for

the

Generati on

of

Dil emma
-
based

Interacti ve

Narrati ves”,

i n

proceedi ng

of

thi rd

Arti fi cial

Intelli gence

for

Interacti ve

Di gi tal

Entertai nment

Conference,

Cal i fornia,

USA,

6
-
8

June,

2007



R
.

Huni cke

and

V
.

Chapman,



AI

for

Dynami c

Di ffi cul ty

Adjustment

i n

Games”,

i n

proceedi ngs

of

the

Chall enges

i n

Game

AI

Workshop,

Ni neteenth

Nati onal

Conference

on

Arti fi ci al

Intel l igence,

San

Jose,

Cal i fornia,

USA,

25
-
29

Jul y,

2004



N
.
A
.
Taatgen
,

and

J
.
R
.
Anderson
,

“Why

do

chi l dren

l earn

to

say

“Broke”?

A

model

of

l earni ng

the

past

tense

wi thout

feedback
.
”,

Cogni ti on,

86
(
2
),
123
-
155
,

December

2002





43

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Bibliography 6/7


D
.

Thue
,

V
.

Bul i tko
,

M
.

Spetch
,

E
.

Wasylishen
,”

Interacti ve

Storytel li ng
:

A

Pl ayer

Modelli ng

Approach”,

i n

proceedi ng

of

thi rd

Arti fi cial

Intelli gence

for

Interacti ve

Di gi tal

Entertai nment

Conference,

Cal i forni a,

USA,

6
-
8

June,

2007



M
.

Kri egel
,

R
.

Ayl ett,

J
.

Di as

and

A
.

Pai v
,

”Learni ng

Player

Preferences

to

Inform

Del ayed

Authori ng”,

i n

AAAI

Symposi um

on
.

Intel li gent

Narrati ve

Technol ogi es
.

Westi n

Arl i ngton

Gateway,

Arl i ngton,

Vi rgi ni a,

9
-
11

November,

2007



P
.

Rani
,

N
.

Sarkar

and

C
.

Li u,

“Mai ntai ni ng

Opti mal

Chall enge

i n

Computer

Games

Through

Real
-
Ti me

Physi ol ogical

Feedback”,

11
th

Human

Computer

Interacti on

Internati onal,

Vegas,

Nevada,

USA,

22
-
27

Jul y

2005



S
.

W
.

McQui ggan
,

S
.

Lee

and

J
.

C
.

Lester,

“Predi cti ng

User

Physi ol ogical

Response

for

Interacti ve

Envi ronments
:

An

Inducti ve

Approach”,

i n

proceedi ng

of

thi rd

Arti fi ci al

Intel ligence

for

Interacti ve

Di gi tal

Entertai nment

Conference,

Cal i fornia,

USA,

20
-
23

June,

2007



R
.

Pi card
,

E
.

Vyzas

and

J
.

Heal ey,

”Toward

machi ne

emoti onal

i ntelli gence
:

anal ysis

of

affecti ve

physi ol ogi cal

state”,

i n

IEEE

Transacti ons

Pattern

Anal ysi s

and

Machi ne

Intel l igence

23
(
10
)
:

1185
-
1191
,
2001



K
.

P
.

Pomsta

and

H
.

Pai n,

“Provi di ng

Cogni ti ve

and

Affecti ve

Scaffol di ng

through

Teachi ng

Strategi es”,

i n

proceedi ngs

of

7
th

Internati onal

Conference

on

Intel l i gent

Tutori ng

Systems,

Macei ó
,

Brazi l,

31
st

August,

2004



H
.
Prendi nger
,

S
.
Mayer
,

J
.
Mori
,

and

M
.
Ishi zuka
,

“Persona

effect

revi si ted
:

Usi ng

bi o
-
si gnals

to

measure

and

refl ect

the

i mpact

of

character
-
based

i nterfaces”,

i n

proceedi ngs

of

4
th

Internati onal

Conference

on

Intel l i gent

Vi rtual

Agents,

Kl oster

Irsee
,

Germany,

15
-
17

September

,

2003



N
.

A
.

Taatgen
,

M
.

V
.

Opl oo
,

J
.

Braaksma
,

J
.

Ni emantsverdri et
,”

How

to

Construct

a

Bel i evabl e

Opponent

usi ng

Cogni ti ve

Model i ng

i n

the

Game

of

Set”,

i n

proceedi ngs

of

the

fi fth

i nternati onal

conference

on

cogni ti ve

model l i ng,

Bamberg,

Germany
.

9
-
12

Apri l,

2003



N
.

Beume
,

B
.

Naujoks
,

G
.

Neugebauer
,

N
.

Pi atkowski

and

M
.

Preuss

,

“CI

enli vened

ghosts

for

Pac
-
Man”,

i n

proceedi ngs

of

IEEE

Computati onal

Intel l i gence

And

Games,

Perth,

Austral i a,

15
-
18

September,

2008


44

FAST
-
National University of Computer and Emerging Sciences, Islamabad

Bibliography 7/7



G
.

V
.

Lankvel d
,

P
.

Spronck
,

and

M
.

Rauterberg
,

”Incongrui ty
-
Based

Adapti ve

Game

Bal anci ng”,

Advances

In

Computer

Games,

Pampl ona,

Spai n,

11

-

13

May

13
,

2009



N
.

Beume
,

T
.

Hei n,

B
.

Naujoks
,

N
.

Pi atkowski
,

M
.

Preuss
,

S
.

Wessi ng
,

“Intel li gent

Anti
-
Groupi ng

i n

Real
-
Ti me

Strategy

Games”,

In

Proceedi ngs

of

IEEE

Computati onal

Intel l i gence

and

Games,

Perth,

Austral i a,

15

-

18

December,

2008



H
.

Dani elsi ek
,

R
.

Stüer
,

A
.

Thom,

N
.

Beume
,

B
.

Naujoks

and

M
.

Preuss
,

“Intelli gent

Movi ng

of

Groups

i n

Real
-
Ti me

Strategy

Games”,

i n

proceedi ngs

of

IEEE

Computati onal

Intel l i gence

And

Games,

Perth,

Austral i a,

15
-
18

September,

2008



M
.

Csi kszentmi hal yi

and

I
.

Csi kszentmi hal yi
,

“Introducti on

to

Part

IV

i n

Opti mal

Experi ence”,

Psychol ogical

Studi es

of

Fl ow

i n

Consci ousness,

Cambri dge,

UK
:

Cambri dge

Uni versi ty

Press
.

1988



T
.

W
.

Mal one,



What

makes

computer

games

fun?”,

ACM

SIGSOC

Bul l eti n,

Vol ume

13

,

Issue

2
-
3

1982



Presentati on

Chess

Pi eces

Image,

https
:
//swansea
-
edunet
.
gov
.
uk/en/school s/Pontarddul ai s/PageImages/Chess
%
20
Piece
.
jpg,

05
-
11
-
2010



Presentati on

background

Images,

http
:
//www
.
presentermedi a
.
com,

05
-
11
-
2010



R
.

Koster
,



A

Theory

of

Fun

for

Game

Desi gn”,

Paragl yph

Press,

2005



D
.

H
.

Ackl ey

and

M
.

L
.

Li ttman,”Interacti ons

between

l earni ng

and

evol uti on”,

In

C
.

G
.

Langton
,

C
.

Tayl or,

J
.

D
.

Farmer,

and

S
.

Rasmussen,

edi tors,

Arti fi ci al

Li fe

II,

pages

478

507
,

Readi ng,

Sante

Fe

Insti tute

Studi es

i n

the

Sci ences

and

Compl exi ty,

Addi son
-
Wesl ey,

MA,

1992




45