A comprehensive survey of multi-agent reinforcement learning


Reference:
L. Busoniu, R. Babuska, and B. De Schutter, "A comprehensive survey of multi-agent reinforcement learning," IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 38, no. 2, pp. 156-172, Mar. 2008.

Abstract:
Multi-agent systems are rapidly finding applications in a variety of domains, including robotics, distributed control, telecommunications, and economics. The complexity of many tasks arising in these domains makes them difficult to solve with preprogrammed agent behaviors. The agents must instead discover a solution on their own, using learning. A significant part of the research on multi-agent learning concerns reinforcement learning techniques. This paper provides a comprehensive survey of multi-agent reinforcement learning (MARL). A central issue in the field is the formal statement of the multi-agent learning goal. Different viewpoints on this issue have led to the proposal of many different goals, among which two focal points can be distinguished: stability of the agents' learning dynamics, and adaptation to the changing behavior of the other agents. The MARL algorithms described in the literature aim-either explicitly or implicitly-at one of these two goals or at a combination of both, in a fully cooperative, fully competitive, or more general setting. A representative selection of these algorithms is discussed in detail in this paper, together with the specific issues that arise in each category. Additionally, the benefits and challenges of MARL are described along with some of the problem domains where MARL techniques have been applied. Finally, an outlook for the field is provided.


Downloads:
 * Online version of the paper
 * Corresponding technical report: pdf file (316 KB)
      Note: More information on the pdf file format mentioned above can be found here.


Bibtex entry:

@article{BusBab:07-019,
        author={L. Bu{\c{s}}oniu and R. Babu{\v{s}}ka and B. {D}e Schutter},
        title={A comprehensive survey of multi-agent reinforcement learning},
        journal={IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews},
        volume={38},
        number={2},
        pages={156--172},
        month=mar,
        year={2008},
        doi={10.1109/TSMCC.2007.913919}
        }



Go to the publications overview page.


This page is maintained by Bart De Schutter. Last update: March 20, 2022.