Open this publication in new window or tab >>2022 (English)In: Proceedings of the 2022 18th International Conference of Network and Service Management: Intelligent Management of Disruptive Network Technologies and Services, CNSM 2022, Institute of Electrical and Electronics Engineers Inc. , 2022, p. 338-344Conference paper, Published paper (Refereed)
Abstract [en]
As design, deployment and operation complexity increase in mobile systems, adaptive self-learning techniques have become essential enablers in mitigation and control of the complexity problem. Artificial intelligence and, in particular, reinforcement learning has shown great potential in learning complex tasks through observations. The majority of ongoing reinforcement learning research activities focus on single-Agent problem settings with an assumption of accessibility to a globally observable state and action space. In many real-world settings, such as LTE or 5G, decision making is distributed and there is often only local accessibility to the state space. In such settings, multi-Agent learning may be preferable, with the added challenge of ensuring that all agents collaboratively work towards achieving a common goal. We present a novel cooperative and distributed actor-critic multi-Agent reinforcement learning algorithm. We claim the approach is sample efficient, both in terms of selecting observation samples and in terms of assignment of credit between subsets of collaborating agents.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2022
Keywords
Machine learning, Radio resource scheduling, 5G mobile communication systems, Adaptive control systems, Decision making, Learning algorithms, Learning systems, Multi agent systems, Continuous reinforcement, Machine-learning, Mobile systems, Multi-agent approach, Radio resources, Reinforcement learnings, Resource-scheduling, Self-learning, State-space, Reinforcement learning
National Category
Computer Sciences
Identifiers
urn:nbn:se:ri:diva-62621 (URN)10.23919/CNSM55787.2022.9965060 (DOI)2-s2.0-85143886726 (Scopus ID)9783903176515 (ISBN)
Conference
18th International Conference of Network and Service Management, CNSM 2022, 31 October 2022 through 4 November 2022
Note
Funding text 1: Kreuger is partially funded by Ericsson. Corcoran and Boman are partially funded by the WASP (Wallenberg Autonomous Systems and Software Program) research program.
2023-01-242023-01-242023-01-24Bibliographically approved