NPCs as People, Too: The Extreme AI Personality Engine

PK Dick once asked “Do Androids Dream of Electric Sheep?” In video games, a similar question could be asked of non-player characters: Do NPCs have dreams? Can they live and change as humans do? Can NPCs have personalities, and can these develop through interactions with players, other NPCs, and the world around them? Despite advances in personality AI for games, most NPCs are still undeveloped and undeveloping, reacting with flat affect and predictable routines that make them far less than human— in fact, they become little more than bits of the scenery that give out parcels of information. This need not be the case. Extreme AI, a psychology-based personality engine, creates adaptive NPC personalities. Originally developed as part of the thesis “NPCs as People: Using Databases and Behaviour Trees to Give Non-Player Characters Personality,” Extreme AI is now a fully functioning personality engine using all thirty facets of the Five Factor model of personality and an AI system that is live throughout gameplay. This paper discusses the research leading to Extreme AI; develops the ideas found in that thesis; discusses the development of other personality engines; and provides examples of Extreme AI’s use in two game demos.

[1]  L. R. Goldberg.  The structure of phenotypic personality traits. , 1993, The American psychologist.

[2]  Domitile Lourdeaux,et al.  Towards a Resource-based Model of Strategy to Help Designing Opponent AI in RTS Games , 2015, ICAART.

[3]  Eric O. Postma,et al.  Adaptive game AI with dynamic scripting , 2006, Machine Learning.

[4]  Michael Mateas,et al.  Comme il Faut: A System for Authoring Playable Social Models , 2011, AIIDE.

[5]  M. Berrow.  Causes and cures , 1991, Nature.

[6]  Kathryn E. Merrick,et al.  Motivated reinforcement learning for non-player characters in persistent computer game worlds , 2006, ACE '06.

[7]  Mat Buckland,et al.  Programming Game AI by Example , 2004 .

[8]  Glenn Curtiss,et al.  The effects of depression and anxiety on memory performance. , 2002, Archives of clinical neuropsychology : the official journal of the National Academy of Neuropsychologists.

[9]  Brian Mac Namee.  Proactive Persistent Agents - Using Situational Intelligence to Create Support Characters in Character-Centric Computer Games , 2004 .

[10]  Sydney Brandon,et al.  The Causes and Cures of Neurosis , 1965 .

[11]  O. John,et al.  Paradigm shift to the integrative Big Five trait taxonomy: History, measurement, and conceptual issues. , 2008 .

[12]  C. DeYoung.  Toward a Theory of the Big Five , 2010 .

[13]  P. Costa,et al.  The five-factor theory of personality. , 2008 .

[14]  P. Costa,et al.  Domains and facets: hierarchical personality assessment using the revised NEO personality inventory. , 1995, Journal of personality assessment.

[15]  B. Roberts,et al.  Personality Trait Change in Adulthood , 2008, Current directions in psychological science.

[16]  Ling Li,et al.  An Emotion-based Adaptive Behavioural Model for Simulated Virtual Agents , 2008, Int. J. Virtual Real..

[17]  A. Mehrabian.  Pleasure-arousal-dominance: A general framework for describing and measuring individual differences in Temperament , 1996 .

[18]  G Saucier,et al.  Hierarchical subcomponents of the Big Five personality factors: a cross-language replication. , 1999, Journal of personality and social psychology.

[19]  Pierre Bessière,et al.  Teaching Bayesian behaviours to video game characters , 2003, Robotics Auton. Syst..

[20]  S. Gosling,et al.  Development of personality in early and middle adulthood: set like plaster or persistent change? , 2003, Journal of personality and social psychology.

[21]  P. Lang.  The emotion probe. Studies of motivation and attention. , 1995, The American psychologist.

[22]  Ling Li,et al.  Emotion modeling and Interaction of NPCS in Virtual Simulation and Games , 2010 .