Priority Based Synchronization for Faster Learning in Games

被引:0
|
作者
Koochakzadeh, Abbasali [1 ]
Yazicioglu, Yasin [1 ]
机构
[1] Univ Minnesota, Dept Elect & Comp Engn, Minneapolis, MN 55455 USA
来源
2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC) | 2022年
关键词
D O I
10.1109/CDC51059.2022.9992513
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Learning in games has been widely used to solve many cooperative multi-agent problems such as coverage control, consensus, self-reconfiguration or vehicle-target assignment. One standard approach in this domain is to formulate the problem as a potential game and to use an algorithm such as log-linear learning to achieve the stochastic stability of globally optimal configurations. Standard versions of such learning algorithms are asynchronous, i.e., only one agent updates its action at each round of the learning process. To enable faster learning, we propose a synchronization strategy based on decentralized random prioritization of agents, which allows multiple agents to change their actions simultaneously when they do not affect each other's utility or feasible actions. We show that the proposed approach can be integrated into any standard asynchronous learning algorithm to improve the convergence speed while maintaining the limiting behavior (e.g., stochastically stable configurations). We support our theoretical results with simulations in a coverage control scenario.
引用
收藏
页码:2500 / 2505
页数:6
相关论文
共 50 条
  • [31] Perfect information stochastic priority games
    Gimbert, Hugo
    Zielonka, Wieslaw
    AUTOMATA, LANGUAGES AND PROGRAMMING, PROCEEDINGS, 2007, 4596 : 850 - +
  • [32] Priority coalitional games and claims problems
    Lugilde, Iago Nunez
    Estevez-Fernandez, Arantza
    Sanchez-Rodriguez, Estela
    MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2024,
  • [33] Improving Priority Promotion for Parity Games
    Benerecetti, Massimo
    Dell'Erba, Daniele
    Mogavero, Fabio
    HARDWARE AND SOFTWARE: VERIFICATION AND TESTING, HVC 2016, 2016, 10028 : 117 - 133
  • [34] Games for learning and learning from games
    Pivec, Maja
    Kearney, Paul
    Informatica (Ljubljana), 2007, 31 (04) : 419 - 423
  • [35] Games for Learning and Learning from Games
    Pivec, Maja
    Kearney, Paul
    INFORMATICA-JOURNAL OF COMPUTING AND INFORMATICS, 2007, 31 (04): : 419 - 423
  • [36] Digital Games in Education: The Design of Games-Based Learning Environments
    Gros, Begona
    JOURNAL OF RESEARCH ON TECHNOLOGY IN EDUCATION, 2007, 40 (01) : 23 - 38
  • [37] Synchronization for Faster Than Nyquist Signalling Transmission
    Kim, Pansoo
    Oh, Deock-Gil
    2015 SEVENTH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS, 2015, : 944 - 949
  • [38] Deterministic priority mean-payoff games as limits of discounted games
    Gimbert, Hugo
    Zielonka, Wieslaw
    AUTOMATA, LANGAGES AND PROGRAMMING, PT 2, 2006, 4052 : 312 - 323
  • [39] Faster algorithms for mean-payoff games
    Brim, L.
    Chaloupka, J.
    Doyen, L.
    Gentilini, R.
    Raskin, J. F.
    FORMAL METHODS IN SYSTEM DESIGN, 2011, 38 (02) : 97 - 118
  • [40] Faster algorithms for mean-payoff games
    L. Brim
    J. Chaloupka
    L. Doyen
    R. Gentilini
    J. F. Raskin
    Formal Methods in System Design, 2011, 38 : 97 - 118