用于模拟选手战术的强化学习羽毛球环境(学生摘要)
机器学习
2022-11-23 v1
摘要
近期精确分析体育赛事的技术激发了多种提升选手表现与观众参与度的途径。然而,现有方法仅能评估离线表现,因为实时比赛中的测试需耗费大量成本且无法复现。为在安全且可复现的模拟器中测试,我们关注回合制运动,并通过以不同视角模拟多拍来回击球、设计状态、动作与训练流程,引入一个羽毛球环境。这不仅通过模拟过往比赛以研究战术而惠及教练与选手,也令研究者得以快速评估其新算法。
引用
@article{arxiv.2211.12234,
title = {A Reinforcement Learning Badminton Environment for Simulating Player Tactics (Student Abstract)},
author = {Li-Chun Huang and Nai-Zen Hseuh and Yen-Che Chien and Wei-Yao Wang and Kuang-Da Wang and Wen-Chih Peng},
journal= {arXiv preprint arXiv:2211.12234},
year = {2022}
}
备注
Accepted by AAAI 2023 Student Abstract, code is available at https://github.com/wywyWang/CoachAI-Projects/tree/main/Strategic%20Environment