Pesce, Emanuele (2023) Learning to communicate in cooperative multi-agent reinforcement learning. PhD thesis, University of Warwick.
Preview |
PDF
WRAP_Theses_Pesce_2023.pdf - Submitted Version - Requires a PDF viewer. Download (14MB) | Preview |
Abstract
Recent advances in deep reinforcement learning have produced unprecedented results. The success obtained on single-agent applications led to exploring these techniques in the context of multi-agent systems where several additional challenges need to be considered. Communication has always been crucial to achieving cooperation in multi-agent domains and learning to communicate represents a fundamental milestone for multi-agent reinforcement learning algorithms. In this thesis, different multi-agent reinforcement learning approaches are explored. These provide architectures that are learned end-to-end and capable of achieving effective communication protocols that can boost the system performance in cooperative settings. Firstly, we investigate a novel approach where intra-agent communication happens through a shared memory device that can be used by the agents to exchange messages through learnable read and write operations. Secondly, we propose a graph-based approach where connectivities are shaped by exchanging pairwise messages which are then aggregated through a novel form of attention mechanism based on a graph diffusion model. Finally, we present a new set of environments with real-world inspired constraints that we utilise to benchmark the most recent state-of-theart solutions. Our results show that communication can be a fundamental tool to overcome some of the intrinsic difficulties that characterise cooperative multi-agent systems.
Item Type: | Thesis [via Doctoral College] (PhD) |
---|---|
Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TJ Mechanical engineering and machinery |
Library of Congress Subject Headings (LCSH): | Multiagent systems, Neural networks (Computer science), Reinforcement learning |
Official Date: | February 2023 |
Dates: | Date Event February 2023 UNSPECIFIED |
Institution: | University of Warwick |
Theses Department: | Warwick Manufacturing Group |
Thesis Type: | PhD |
Publication Status: | Unpublished |
Supervisor(s)/Advisor: | Montana, Giovanni |
Sponsors: | University of Warwick |
Format of File: | |
Extent: | xiii, 124 pages : illustrations |
Language: | eng |
URI: | https://wrap.warwick.ac.uk/179925/ |
Request changes or add full text files to a record
Repository staff actions (login required)
![]() |
View Item |