Cooperation is a challenging task as balancing the desired outcome for a group of autonomous agents while they perceive/act based on their own point of view poses an interesting research question. Many approaches have been proposed for dealing with this issue using Deep Reinforcement Learning (DRL) solutions, where the agents learn how to weigh their decisions based on the group's interests. In such solutions, the design of the reward functions for multi-agent DRL problems is an area that is still open to be explored given the complexity of the analysis and the environment-agents relationships. In this work, we propose the application of the Vickrey-Clarke-Groves mechanism design principles to derive reward functions to be applied during the training of autonomous agents in a cooperative multiple pursuer-evader game scenario. Such economic theory is very promising given the capability of incentivizing and penalizing agent's behaviour given the impact of their actions on the whole group. Our results show that the proposed reward scheme causes the agents to learn faster and to be more effective in achieving solutions to the pursuer-evader problem when compared to DRL solutions using traditional reward functions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Improved Learning in Multi-Agent Pursuer-Evader UAV Scenarios via Mechanism Design and Deep Reinforcement Learning




    Publication date :

    2024-06-04


    Size :

    518630 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multi-Pursuer Multi-Evader Pursuit-Evasion Games with Jamming Confrontation

    Mo Wei / Genshe Chen / Jose Cruz et al. | AIAA | 2007


    Impact of Disparate Goals on Evader Performance in an Orbital Pursuer-Evader Game

    Halsey, Stephanie / Curtis, David / Prince, Eric | AIAA | 2024


    Two-Pursuer, One-Evader Pursuit Evasion Differential Game

    Fuchs, Zachariah E. / Garcia, Eloy / Casbeer, David W. | IEEE | 2018


    Multiple Pursuer Single Evader Border Defense Differential Game

    Von Moll, Alexander L. / Garcia, Eloy / Casbeer, David et al. | AIAA | 2019


    Multiple-Pursuer, Single-Evader Border Defense Differential Game

    Von Moll, Alexander / Garcia, Eloy / Casbeer, David et al. | AIAA | 2020