A Fighting Game AI Using Highlight Cues for Generation of Entertaining Gameplay

In this paper, we propose a fighting game AI that selects its actions from the perspective of highlight generation using Monte-Carlo tree search (MCTS) with three highlight cues in the evaluation function. The proposed AI is targeted for being used to generate gameplay in live streaming platforms such as Twitch and YouTube where a large number of spectators watch gameplay to entertain themselves. Our results in a user study conducted using FightingICE, a fighting game platform used in an international game AI competition since 2013, show that gameplay generated by the proposed AI is more entertaining than that by a typical MCTS AI. Detailed analyses of gameplay from all the methods assessed in the user study are also given in the paper.

[1]  Ruck Thawonmas,et al.  Monte-Carlo Tree Search for Implementation of Dynamic Difficulty Adjustment Fighting Game AIs Having Believable Behaviors , 2018, 2018 IEEE Conference on Computational Intelligence and Games (CIG).

[2]  Ruck Thawonmas,et al.  Application of Monte-Carlo tree search in a fighting game AI , 2016, 2016 IEEE 5th Global Conference on Consumer Electronics.

[3]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[4]  Ruck Thawonmas,et al.  AI for Game Spectators: Rise of PPG , 2017, AAAI Workshops.

[5]  Kokolo Ikeda,et al.  Adaptive Fighting Game Computer Player by Switching Multiple Rule-Based Controllers , 2015, 2015 3rd International Conference on Applied Computing and Information Technology/2nd International Conference on Computational Science and Intelligence.

[6]  Kyung-Joong Kim,et al.  Learning to play fighting game using massive play data , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[7]  Mark O. Riedl,et al.  Automatic playtesting for game parameter tuning via active learning , 2019, FDG.

[8]  Kyung-Joong Kim,et al.  Deep Q networks for visual fighting game AI , 2017, 2017 IEEE Conference on Computational Intelligence and Games (CIG).

[9]  Xiaodong Li,et al.  Monte Carlo tree search based algorithms for dynamic difficulty adjustment , 2017, 2017 IEEE Conference on Computational Intelligence and Games (CIG).

[10]  Ruck Thawonmas,et al.  Fighting game artificial intelligence competition platform , 2013, 2013 IEEE 2nd Global Conference on Consumer Electronics (GCCE).

[11]  Günter Rudolph,et al.  Advanced Dynamic Scripting for Fighting Game AI , 2015, ICEC.

[12]  Masayuki Numao,et al.  Prediction as faster perception in a real-time fighting video game , 2015, 2015 IEEE Conference on Computational Intelligence and Games (CIG).

[13]  Charles Ringer,et al.  Deep unsupervised multi-view detection of video game stream highlights , 2018, FDG.

[14]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[15]  Rémi Coulom,et al.  Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search , 2006, Computers and Games.

[16]  C. Jaruskulchai,et al.  Flashlight and player detection in fighting sport for video summarization , 2005, IEEE International Symposium on Communications and Information Technology, 2005. ISCIT 2005..

[17]  Sam Devlin,et al.  Combining Gameplay Data with Monte Carlo Tree Search to Emulate Human Play , 2016, AIIDE.

[18]  Kokolo Ikeda,et al.  Optimized Non-visual Information for Deep Neural Network in Fighting Game , 2017, ICAART.

[19]  Juho Hamari,et al.  What is eSports and why do people watch it? , 2017, Internet Res..

[20]  Simon M. Lucas,et al.  Open Loop Search for General Video Game Playing , 2015, GECCO.

[21]  Ruck Thawonmas,et al.  Applying Hybrid Reward Architecture to a Fighting Game AI , 2018, 2018 IEEE Conference on Computational Intelligence and Games (CIG).

[22]  Irfan A. Essa,et al.  Leveraging Contextual Cues for Generating Basketball Highlights , 2016, ACM Multimedia.

[23]  Kyung-Joong Kim,et al.  Opponent modeling based on action table for MCTS-based fighting game AI , 2017, 2017 IEEE Conference on Computational Intelligence and Games (CIG).

[24]  Sanaz Mostaghim,et al.  HTN fighter: Planning in a highly-dynamic game , 2017, 2017 9th Computer Science and Electronic Engineering (CEEC).