Machine learning (ML) is becoming ubiquitous in real-world applications, spanning from our domestic devices such as vacuum cleaner robots, smart phones, virtual assistants, to industrial applications such as manipulators, warehouse robots, to public services such as medical imaging, surveillance cameras, energy grid, etc. With the growing ubiquity and interconnection of these devices, interactions among them will soon become commonplace. These emerging ML problems and the interactions among agents can be formulated as Multiagent ML Systems. On the one hand, many complex ML tasks require the cooperation among multiple agents carrying distributed resources and capabilities. On the other hand, multiagent solutions often lead to improved efficiency, robustness and scalability. Among the many aspects of multiagent ML systems, an important research problem is payoff allocation. This is because multiagent ML systems typically receive a global payoff for the overall performance of all agents, while a fine-grained evaluation of each agent's contribution is absent. Nevertheless, these agent-specific payoffs not only offer natural incentives for their contribution and cooperation, but also provide crucial feedback signals for interpreting the agent's contributions and improving the their future cooperative policies. In this thesis, we investigate the properties of emerging multiagent ML systems and address new challenges that arise when applying classic payoff allocation methods from cooperative game theory to them. The first part of the thesis investigates payoff allocation in submodular multiagent ML problems. Though convex games are commonly studied in cooperative game theory, many multiagent ML applications naturally exhibit submodular characteristics. Moreover, properties of the ML applications give rise to increased computational burden, as well as a new type of malicious attack (i.e., the replication manipulation). To address these challenges, we present a theoretical analysis on payoff allocation methods (in ...


    Access

    Download


    Export, share and cite



    Title :

    Game-theoretic payoff allocation in multiagent machine learning systems


    Contributors:

    Publication date :

    2022-05-13


    Type of media :

    Theses


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning

    Lanctot, M / Zambaldi, V / Gruslys, A et al. | BASE | 2017

    Free access

    PREMIUM PAYOFF

    Feldman, Joan M. | Online Contents | 1998


    Collaboration Payoff

    Thomas, Geoffrey | Online Contents | 2011


    Game theoretic power allocation and waveform selection for satellite communications

    Shu, Zhihui / Wang, Gang / Tian, Xin et al. | SPIE | 2015


    Game Theoretic subcarrier and power allocation for wireless OFDMA networks

    Zhang, G. P. / Zhong, Y. L. / Ding, E. J. | British Library Online Contents | 2012