Yin Gu
Enhong Chen
ABSTRACT
In online games, predicting massive battle outcomes is a fundamental task of many applications, such as team optimization and tactical formulation. Existing works do not pay adequate attention to the massive battle. They either seek to evaluate individuals in isolation or mine simple pair-wise interactions between individuals, neither of which effectively captures the intricate interactions between massive units (e.g., individuals). Furthermore, as the team size increases, the phenomenon of diminishing marginal utility of units emerges. Such a diminishing pattern is rarely noticed in previous work, and how to capture it from data remains a challenge. To this end, we propose a novel Massive battle outcome predictor with margiNal Effect modules, namely MassNE, which comprehensively incorporates individual effects, cooperation effects (i.e., intra-team interactions) and suppression effects (i.e., inter-team interactions) for predicting battle outcomes. Specifically, we design marginal effect modules to learn how units’ marginal utility changing respect to their number, where the monotonicity assumption is applied to ensure rationality. In addition, we evaluate the current classical models and provide mathematical proofs that MassNE is able to generalize several earlier works in massive settings. Massive battle datasets generated by StarCraft II APIs are adopted to evaluate the performances of MassNE. Extensive experiments empirically demonstrate the effectiveness of MassNE, and MassNE can reveal reasonable cooperation effects, suppression effects, and marginal utilities of combat units from the data.
- Dimitri P Bertsekas. 2014. Constrained optimization and Lagrange multiplier methods. Academic press.Google Scholar
- Andrew P Bradley. 1997. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern recognition 30, 7 (1997), 1145–1159.Google ScholarDigital Library
- Ralph Allan Bradley and Milton E Terry. 1952. Rank analysis of incomplete block designs: I. The method of paired comparisons. Biometrika 39, 3/4 (1952), 324–345.Google ScholarCross Ref
- Shuo Chen and Thorsten Joachims. 2016. Modeling intransitivity in matchup and comparison data. In Proceedings of WSDM. 227–236.Google ScholarDigital Library
- Zhengxing Chen, Truong-Huy D Nguyen, Yuyu Xu, Christopher Amato, Seth Cooper, Yizhou Sun, and Magy Seif El-Nasr. 2018. The art of drafting: a team-oriented hero recommendation system for multiplayer online battle arena games. In Proceedings of the 12th ACM Conference on Recommender Systems. 200–208.Google ScholarDigital Library
- Zhengxing Chen, Yuyu Xu, Truong-Huy D Nguyen, Yizhou Sun, and Magy Seif El-Nasr. 2018. Modeling game avatar synergy and opposition through embedding in multiplayer online battle arena games. arXiv preprint arXiv:1803.10402 (2018).Google Scholar
- David Churchill, Abdallah Saffidine, and Michael Buro. 2012. Fast heuristic search for RTS game combat scenarios. In Eighth Artificial Intelligence and Interactive Digital Entertainment Conference.Google ScholarDigital Library
- Olivier Delalleau, Emile Contal, Eric Thibodeau-Laufer, Raul Chandias Ferrari, Yoshua Bengio, and Frank Zhang. 2012. Beyond skill rating: Advanced matchmaking in ghost recon online. IEEE Transactions on Computational Intelligence and AI in Games 4, 3 (2012), 167–177.Google ScholarCross Ref
- Aram Ebtekar and Paul Liu. 2021. Elo-MMR: A Rating System for Massive Multiplayer Competitions. In Proceedings of the Web Conference 2021. 1772–1784.Google ScholarDigital Library
- Arpad E Elo. 1978. The rating of chessplayers, past and present. Arco Pub.Google Scholar
- Donelson R Forsyth. 2018. Group dynamics. Cengage Learning.Google Scholar
- Mark E Glickman. 1999. Parameter estimation in large dynamic paired comparison experiments. Journal of the Royal Statistical Society: Series C (Applied Statistics) 48, 3 (1999), 377–394.Google ScholarCross Ref
- Linxia Gong, Xiaochuan Feng, Dezhi Ye, Hao Li, Runze Wu, Jianrong Tao, Changjie Fan, and Peng Cui. 2020. OptMatch: Optimized Matchmaking via Modeling the High-Order Interactions on the Arena. In SIGKDD. 2300–2310.Google Scholar
- Boris Groysberg, Jeffrey T Polzer, and Hillary Anger Elfenbein. 2011. Too many cooks spoil the broth: How high-status individuals decrease group effectiveness. Organization Science 22, 3 (2011), 722–737.Google ScholarDigital Library
- Yin Gu, Qi Liu, Kai Zhang, Zhenya Huang, Runze Wu, and Jianrong Tao. 2021. Neuralac: Learning cooperation and competition effects for match outcome prediction. In AAAI, Vol. 35. 4072–4080.Google Scholar
- Bartosz Gula, Nemanja Vaci, Rainer W Alexandrowicz, and Merim Bilalic. 2021. Never too much-The benefit of talent to team performance in the National Basketball Association: Comment on Swaab, Schaerer, Anicich, Ronay, and Galinsky (2014). Psychological science 32, 2 (2021), 301–304.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision. 1026–1034.Google ScholarDigital Library
- Xiangnan He and Tat-Seng Chua. 2017. Neural factorization machines for sparse predictive analytics. In ACM SIGIR. 355–364.Google Scholar
- Ralf Herbrich, Tom Minka, and Thore Graepel. 2007. TrueSkill: a Bayesian skill rating system. In NeurIPS. 569–576.Google Scholar
- Jie Huang, Qi Liu, Fei Wang, Zhenya Huang, Songtao Fang, Runze Wu, Enhong Chen, Yu Su, and Shijin Wang. 2021. Group-Level Cognitive Diagnosis: A Multi-Task Learning Perspective. In 2021 IEEE International Conference on Data Mining (ICDM). IEEE, 210–219.Google Scholar
- Tzu-Kuo Huang, Chih-Jen Lin, and Ruby C Weng. 2008. Ranking individuals by group comparisons. JMLR 9, Oct (2008), 2187–2216.Google Scholar
- James Kennedy. 2006. Swarm intelligence. Springer.Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Alexander Kovarsky and Michael Buro. 2005. Heuristic search applied to abstract combat games. In Conference of the Canadian Society for Computational Studies of Intelligence. Springer, 66–78.Google ScholarDigital Library
- Anders Krogh and John A Hertz. 1992. A simple weight decay can improve generalization. In NeurIPS. 950–957.Google Scholar
- Frederick William Lanchester. 1916. Aircraft in warfare: The dawn of the fourth arm. Constable limited.Google Scholar
- Richard Layard, Guy Mayraz, and Stephen Nickell. 2008. The marginal utility of income. Journal of Public Economics 92, 8-9 (2008), 1846–1857.Google ScholarCross Ref
- Donghyeon Lee, Man-Je Kim, and Chang Wook Ahn. 2020. Battlenet: Capturing advantageous battlefield in RTS games (student abstract). In AAAI, Vol. 34. 13849–13850.Google Scholar
- Donghyeon Lee, Man-Je Kim, and Chang Wook Ahn. 2021. Predicting combat outcomes and optimizing armies in StarCraft II by deep learning. Expert Systems with Applications 185 (2021), 115592.Google ScholarDigital Library
- Hojoon Lee, Dongyoon Hwang, Hyunseung Kim, Byungkun Lee, and Jaegul Choo. 2022. DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games. In ACM Web Conference. 3428–3439.Google Scholar
- Yao Li, Minhao Cheng, Kevin Fujii, Fushing Hsieh, and Cho-Jui Hsieh. 2018. Learning from group comparisons: exploiting higher order interactions. In NeurIPS. 4981–4990.Google Scholar
- Tom Minka, Ryan Cleven, and Yordan Zaykov. 2018. Trueskill 2: An improved bayesian skill rating system. Tech. Rep. (2018).Google Scholar
- Jordan Michael I Ng, Andrew Y. 2002. On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. In NeurIPS. 841–848.Google Scholar
- Santiago Ontanón, Gabriel Synnaeve, Alberto Uriarte, Florian Richoux, David Churchill, and Mike Preuss. 2013. A survey of real-time strategy game AI research and competition in StarCraft. IEEE Transactions on Computational Intelligence and AI in games 5, 4 (2013), 293–311.Google ScholarCross Ref
- Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. In NeurIPS. 8026–8037.Google Scholar
- Robert S Pindyck and Daniel L Rubinfeld. 2014. Microeconomics. Pearson Education.Google Scholar
- Dongning Ren, Olga Stavrova, and Wen Wei Loh. 2022. Nonlinear effect of social interaction quantity on psychological well-being: Diminishing returns or inverted U¿Journal of Personality and Social Psychology 122, 6 (2022), 1056.Google Scholar
- Steffen Rendle. 2010. Factorization machines. In ICDM. IEEE, 995–1000.Google Scholar
- Mikayel Samvelyan, Tabish Rashid, Christian Schroeder De Witt, Gregory Farquhar, Nantas Nardelli, Tim GJ Rudner, Chia-Man Hung, Philip HS Torr, Jakob Foerster, and Shimon Whiteson. 2019. The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019).Google Scholar
- Aleksandr Semenov, Peter Romov, Sergey Korolev, Daniil Yashkov, and Kirill Neklyudov. 2016. Performance of machine learning algorithms in predicting game outcome from drafts in Dota 2. In International Conference on Analysis of Images, Social Networks and Texts. Springer, 26–37.Google Scholar
- Dennis Soemers. 2014. Tactical planning using MCTS in the game of StarCraft. Master’s thesis, Maastricht University (2014).Google Scholar
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1 (2014), 1929–1958.Google ScholarDigital Library
- Roderick I Swaab, Michael Schaerer, Eric M Anicich, Richard Ronay, and Adam D Galinsky. 2014. The too-much-talent effect: Team interdependence determines when more talent is too much or not enough. Psychological Science 25, 8 (2014), 1581–1591.Google ScholarCross Ref
- Richard Tay. 2008. Marginal effect of increasing ageing drivers on injury crashes. Accident Analysis & Prevention 40, 6 (2008), 2065–2068.Google ScholarCross Ref
- Alberto Uriarte and Santiago Ontanón. 2015. Automatic learning of combat models for RTS games. In Eleventh artificial intelligence and interactive digital entertainment conference.Google Scholar
- Alberto Uriarte and Santiago Ontanón. 2017. Combat models for RTS games. IEEE TOG 10, 1 (2017), 29–41.Google Scholar
- Oriol Vinyals, Igor Babuschkin, Wojciech M Czarnecki, Michaël Mathieu, Andrew Dudzik, Junyoung Chung, David H Choi, Richard Powell, Timo Ewalds, Petko Georgiev, 2019. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 7782 (2019), 350–354.Google Scholar
- Fei Wang, Qi Liu, Enhong Chen, Zhenya Huang, Yu Yin, Shijin Wang, and Yu Su. 2022. NeuralCD: A General Framework for Cognitive Diagnosis. IEEE Transactions on Knowledge and Data Engineering (2022).Google Scholar
- Zelong Yang, Zhufeng Pan, Yan Wang, Deng Cai, Shuming Shi, Shao-Lun Huang, Wei Bi, and Xiaojiang Liu. 2022. Interpretable Real-Time Win Prediction for Honor of Kings–a Popular Mobile MOBA Esport. IEEE TOG (2022).Google ScholarCross Ref
- Kai Zhang, Hao Qian, Qing Cui, Qi Liu, Longfei Li, Jun Zhou, Jianhui Ma, and Enhong Chen. 2021. Multi-interactive attention network for fine-grained feature learning in ctr prediction. In Proceedings of the 14th ACM international conference on web search and data mining. 984–992.Google ScholarDigital Library
- Chuang Zhao, Hongke Zhao, Yong Ge, Runze Wu, and Xudong Shen. 2022. Winning Tracker: A New Model for Real-time Winning Prediction in MOBA Games. In ACM Web Conference. 3387–3395.Google Scholar
Index Terms
- MassNE: Exploring Higher-Order Interactions with Marginal Effect for Massive Battle Outcome Prediction
Recommendations
Integration of simulations, battle command, and technology
SIW '09: Proceedings of the 2009 SISO European Simulation Interoperability WorkshopThe 2008 SIMCI Combined project resulted in a successful robust demonstration of integration of Battle Command, Simulations, and emerging Technology. The 2009 SIMCI Combined project is being executed by a team from Project Manager Battle Command (PM BC),...
Comments