Multi-Agent Reinforcement Learning for Multiscale Unmanned Systems
A special issue of Computers (ISSN 2073-431X).
Deadline for manuscript submissions: closed (31 July 2023) | Viewed by 258
Special Issue Editor
Special Issue Information
Dear Colleagues,
With the advances made in low-cost sensors and embedded systems, multiscale unmanned systems (MUS), comprised of tens, hundreds, or even thousands of autonomous mobile robots, are becoming a viable solution for conducting long-duration autonomous tasks over large regions of interest. Such tasks entail many mobile robots cooperating to complete common tasks based on information/data sharing and fusion among robots, including robotic swarm navigation, information collection, large-scale search and rescue, and multi-agent-multi-target surveillance. Due to complex and time-varying real environments, the practical MUS problems always be formulated and solved by multi-agent reinforcement learning (MARL) approaches. This Special Issue (Multi-Agent Reinforcement Learning for Multiscale Unmanned Systems) aims to highlight the latest research in MARL and its applications in MUS. The main topics of the Special Issue are as follows:
- Statistical models of multiscale unmanned systems problems, including MUS, time-varying environments, and multiple tasks;
- MARL algorithms for MUS based on random finite sets (RFS);
- Approximated dynamic programming for MUS;
- Online MARL algorithms with exploration-exploitation;
- Robotic swarm navigation in dynamic environments;
- MARL algorithms for large-scale search and rescue;
- MARL algorithms for multi-agent multi-target surveillance;
- Human and MUS collaboration and interface
Dr. Pingping Zhu
Guest Editor
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Computers is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- multi-agent reinforcement learning (MARL)
- approximate dynamic programming (ADP)
- multiscale-Unmanned Systems (MUS)
- multi-Agent-Multi-Target (MAMT)
