|
TECHNICAL SCIENCE
Classification of multi-agent reinforcement
learning problems
V. I. Petrenko Federal State Autonomous Educational Institution for Higher Education
«North-Caucasus Federal University»,
355017, Stavropol region, Stavropol, 1 Pushkin str.
Abstract:
With the advent of deep single-agents reinforcement learning (SARL), multi-agent reinforcement
learning (MARL) has received a new impetus for development in the form of deep multi-agent reinforcement learning (MDRL). The active development of methods in this area over the past few years has actualized the issues of their systematization and classification. Existing works use the mechanisms used in
the corresponding MDRL methods as classification signs. However, the applicability of a particular
method is determined not only by the class of the method, but also by the class of the MARL problem. The
purpose of this work is to formalize and classify MARL tasks. To achieve the goal, the mathematical formalization and generalization of the existing classifications of SARL tasks is carried out. The peculiarities arising in the transition from the SARL problem to the MARL problem are considered and mathematically formalized. The essential features are highlighted and the classification of MARL tasks is carried
out on the basis of the set-theoretic approach. The use of the set-theoretic approach made it possible to
identify classes of MARL problems, generalized in other similar works, but possessing specific properties,
which can be used to develop more efficient methods for solving such MARL problems. It is expected that
the proposed formalism and classification of MARL problems will be useful for researchers as a tool for
setting a problem and determining the place of research in the general structure of MARL methods and
tasks, and will also be useful for developers for a reasonable choice of MARL methods based on the class
of the problem being solved.
Keywords:
multi-agent reinforcement learning, multi-agent systems, classification.
Received: 27.05.2021
Citation:
V. I. Petrenko, “Classification of multi-agent reinforcement
learning problems”, News of the Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences, 2021, no. 3, 32–44
Linking options:
https://www.mathnet.ru/eng/izkab354 https://www.mathnet.ru/eng/izkab/y2021/i3/p32
|
Statistics & downloads: |
Abstract page: | 105 | Full-text PDF : | 160 | References: | 13 |
|