OptMatch: Optimized matchmaking via modeling the high-order interactions on the arena

Abstract: Matchmaking is a core problem for the e-sports and online games, which determines the player satisfaction and further influences the life cycle of the gaming products. Most of matchmaking systems take the form of grouping the queuing players into two opposing teams by following certain rules. The design and implementation of matchmaking systems are usually product-specific and labor-intensive.This paper proposes a two-stage data-driven matchmaking framework (namely OptMatch), which is applicable to most of gaming products and has the minimal product knowledge required. OptMatch contains an offline learning stage and an online planning stage. The offline learning stage includes (1) relationship mining modules to learn the low-dimensional representations of individuals by capturing the high-order inter-personal interactions, and (2) a neural network to incorporate the team-up effect and predict the match outcomes. The online planning stage optimizes the gross player utilities (i.e., satisfaction) during the matchmaking process, by leveraging the learned representations and predictive model.Quantitative evaluations on four real-world datasets and an online experiment on Fever Basketball game are conducted to empirically demonstrate the effectiveness of OptMatch.

19/10/2020

Match tracing: A unified framework for real-time win prediction and quantifiable performance evaluation

Kai Wang, Hao Li, Linxia Gong and
Jianrong Tao, Runze Wu, Changjie Fan, Liang Chen, Peng Cui

A limited-capacity minimax theorem for non-convex games or: How i learned to stop worrying about mixed-nash and love neural nets

large displays, shared spaces, loosely-coupled interaction, physical territory, digital territory, collaboration and group work, games and entertainment software

9:54

02/02/2021

Algorithms -> Large Scale Learning; Optimization -> Convex Optimization; Theory -> Learning Theory; Theory -> Spaces of Functio, Algorithms -> Kernel Methods

3:21

22/09/2020

Ashutosh Adhikari, Eric Yuan, Marc-Alexandre Côté and
Mikuláš Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, Will Hamilton

Yiming Gao, Bei Shi, Xueying Du and
Liang Wang, Guangwei Chen, Zhenjie Lian, Fuhao Qiu, GUOAN HAN, Weixuan Wang, Deheng Ye, Qiang Fu, Wei Yang, Lanxiao Huang

David Mguni, Yutong Wu, Yali Du and
Yaodong Yang, Ziyi Wang, M. Li, Ying Wen, Joel Jennings, Jun Wang

Paul Muller, Shayegan Omidshafiei, Mark Rowland and
Karl Tuyls, Julien Perolat, Siqi Liu, Daniel Hennes, Luke Marris, Marc Lanctot, Edward Hughes, Zhe Wang, Guy Lever, Nicolas Heess, Thore Graepel, Remi Munos

Xu HE, Bo An, Yanghua Li and
Haikai Chen, Rundong Wang, Xinrun Wang, Runsheng Yu, Xin Li, Zhirong Wang

DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes

Seyed Abolfazl Ghasemzadeh, Gabriel Van Zandycke, Maxime Istasse and
Niels Sayez, Amirafshar Moshtaghpour, Christophe De Vleeschouwer

Keywords Paper

instance segmentation, ball detection, pose estimation, team sport, sport scenes, multitask learning, multi-task learning, multi task learning, basketball, COCO, DeepSport, panoptic quality

2:53

18/07/2021