HTN or State Space - Who Should Do Planning in Your Game?

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F13%3A10210063" target="_blank" >RIV/00216208:11320/13:10210063 - isvavai.cz</a>

Výsledek na webu

<a href="http://artemis.ms.mff.cuni.cz/main/papers/2013-pddl_vs_htn.pdf" target="_blank" >http://artemis.ms.mff.cuni.cz/main/papers/2013-pddl_vs_htn.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

HTN or State Space - Who Should Do Planning in Your Game?

Popis výsledku v původním jazyce

There is an ongoing discussion in the game AI community, whether to use AI planning for controlling non-player characters (NPCs) in computer games. Recent years have seen implementations of both state space and hierarchical task network (HTN) planning inAAA game titles, each having specific advantages and disadvantages. This paper is concerned with the performance aspect of both technologies and proposes a general methodology for comparing performance of action selection mechanisms. Two case studies comparing NPCs controlled by the JSHOP2 HTN planner and SGPlan 6 and Metric-FF state space planners in a game-like competitive environment are presented and their results are statistically analyzed. First environment is a puzzle-like scenario with minor combat element and strong competition for limited resources. Second environment features two pairs of cooperating agents in a combat scenario inspired by the Gears of War series. It is concluded that in puzzle-like domains HTN planning is i

Název v anglickém jazyce

HTN or State Space - Who Should Do Planning in Your Game?

Popis výsledku anglicky

There is an ongoing discussion in the game AI community, whether to use AI planning for controlling non-player characters (NPCs) in computer games. Recent years have seen implementations of both state space and hierarchical task network (HTN) planning inAAA game titles, each having specific advantages and disadvantages. This paper is concerned with the performance aspect of both technologies and proposes a general methodology for comparing performance of action selection mechanisms. Two case studies comparing NPCs controlled by the JSHOP2 HTN planner and SGPlan 6 and Metric-FF state space planners in a game-like competitive environment are presented and their results are statistically analyzed. First environment is a puzzle-like scenario with minor combat element and strong competition for limited resources. Second environment features two pairs of cooperating agents in a combat scenario inspired by the Gears of War series. It is concluded that in puzzle-like domains HTN planning is i

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/GAP103%2F10%2F1287" target="_blank" >GAP103/10/1287: PlanEx: Propojení plánování a provádění plánů</a><br>

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2013

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

14th International Conference on Intelligent Games and Simulation, GAME-ON 2013

ISBN

978-90-77381-80-9

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

59-65

Název nakladatele

EUROSIS

Místo vydání

Ghent, Belgie

Místo konání akce

Brusel, Belgie

Datum konání akce

25. 11. 2013

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—