62nd IEEE Conference on Decision and Control
Distributed Control, Optimization and Learning for Multi-agent Systems
Pre-Conference Workshop, December 12, 2023
Rapid developments in digital systems, communication technologies, and sensing devices have led to the emergence of large-scale networked systems connecting a massive number of intelligent agents. Motivated by applications such as control, decision-making, machine learning, and signal processing in these networked systems, the agents are often required to jointly solve control, optimization and learning problems so that a desirable intelligent system can operate effectively in complex and dynamic environments will be achieved.
Due to the distributed nature of the networked systems, the traditional centralized strategies are not suitable to address those optimization problems, as they suffer from performance limitations such as vulnerability to single-point failures, costly communications and computations, and lack of flexibility and scalability. This motivates the development of distributed control, optimization and learning algorithms for multi-agent systems.
Distributed control, optimization, and learning are essential techniques for enabling multi-agent systems to operate efficiently and robustly. Distributed control involves designing decentralized control policies that allow individual agents to make decisions based on local information while coordinating with other agents to achieve a common objective. Optimization techniques can be used to find optimal solutions for complex problems that involve multiple agents and conflicting objectives. Learning algorithms can enable agents to improve their behavior over time based on past experiences.
The objective of this workshop is to provide a platform for researchers to exchange ideas and share recent developments in distributed control, optimization and learning for multi-agent systems. The workshop will feature invited talks from leading researchers in the field. We believe that this workshop will provide an excellent opportunity for researchers and practitioners to exchange ideas, and advance the state-of-the-art in multi-agent systems.