Desirable Behaviors for Companion Bots in First-Person Shooters

First-Person Shooter games are a popular genre that often includes a team deathmatch mode of play: teams of agents score by killing members of the other team. When played without other humans, this mode features both opponent bots and companion bots. This paper uses a human subject study with 30 participants to analyze player preference for cooperative teammates vs. skilled, but less cooperative, teammates in the game Unreal Tournament 2004. Specifically, participants play with both a skilled bot based on neuroevolution and a less skilled bot hand-coded to be more cooperative. Survey results indicate that users perceived significant differences between the bots in several categories, e.g. following behavior and skill at scoring, but did not have a significant preference for one bot over another. However, participants did significantly prefer whichever bot they personally felt was more "helpful" and also preferred whichever bot they happened to see more of. These data indicate how user perception can strongly depend on coincidental interactions, such as being seen more. They also identify some qualities that humans desire in teammates, and indicate that simply scoring more will not necessarily result in a higher user preference.

[1]  Philip Hingston,et al.  A new design for a Turing Test for Bots , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[2]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[3]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[4]  Kenneth O. Stanley and Bobby D. Bryant and Risto Miikkulainen,et al.  Real-Time Evolution in the NERO Video Game (Winner of CIG 2005 Best Paper Award) , 2005, CIG.

[5]  Mihai Polceanu,et al.  MirrorBot: Using human-inspired mirroring behavior to pass a turing test , 2013, 2013 IEEE Conference on Computational Inteligence in Games (CIG).

[6]  John E. Laird,et al.  Human-Level AI's Killer Application: Interactive Computer Games , 2000, AI Mag..

[7]  Philip Hingston,et al.  A Turing Test for Computer Game Bots , 2009, IEEE Transactions on Computational Intelligence and AI in Games.

[8]  Kevin McGee,et al.  Real-time team-mate AI in games: a definition, survey, & critique , 2010, FDG.

[9]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[10]  Risto Miikkulainen,et al.  Believable Bot Navigation via Playback of Human Traces , 2012, Believable Bots.

[11]  Risto Miikkulainen,et al.  Discovering Multimodal Behavior in Ms. Pac-Man Through Evolution of Modular Neural Networks , 2016, IEEE Transactions on Computational Intelligence and AI in Games.

[12]  Simon Colton,et al.  Intrinsically motivated general companion NPCs via Coupled Empowerment Maximisation , 2016, 2016 IEEE Conference on Computational Intelligence and Games (CIG).

[13]  Rudolf Kadlec,et al.  Pogamut 3 Can Assist Developers in Building AI (Not Only) for Their Videogame Agents , 2009, AGS.

[14]  R. Miikkulainen,et al.  Humanlike Combat Behavior via Multiobjective , 2018 .

[15]  Kathryn E. Merrick,et al.  Motivated Reinforcement Learning - Curious Characters for Multiuser Games , 2009 .

[16]  Julian Togelius,et al.  Hierarchical controller learning in a First-Person Shooter , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[17]  Christina Backes,et al.  EDISON-WMW: Exact Dynamic Programing Solution of the Wilcoxon–Mann–Whitney Test , 2016, Genom. Proteom. Bioinform..

[18]  Risto Miikkulainen,et al.  An Integrated Neuroevolutionary Approach to Reactive Control and High-Level Strategy , 2012, IEEE Trans. Evol. Comput..

[19]  Kevin McGee,et al.  AI for dynamic team-mate adaptation in games , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[20]  P. Hingston.  Believable Bots: Can Computers Play Like People? , 2012 .

[21]  Risto Miikkulainen,et al.  UT2: Human-like behavior via neuroevolution of combat behavior and replay of human traces , 2011, CIG.