Developing efficient methods for multiagent learning has been a long-standing research focus in the Artificial intelligence, Game theory, Control, and Neuroscience communities. As a growing number of agents are deployed in complex environments for scientific research and human well-being, there are increasing demands to design efficient learning algorithms that can be used in these real-world settings (including accounting for uncertainty, partial observability, sequential settings and communication restrictions). These challenges exist in many domains, such as underwater exploration, planetary navigation, robot soccer, stock-trading systems, and e-commerce.
Multiagent learning has had many successes, but significant challenges remain. For this symposium, we are interested in improving methods and integrating methods for different areas of AI. Topics of interest include:
- Learning in sequential settings in dynamic environments (such as stochastic games, decentralized POMDPs and their variants)
- Learning with partial observability
- Learning with various communication limitations
- Learning in ad-hoc teamwork scenarios
- Scalability through swarms vs. intelligent agents
- Bayesian nonparametric methods for multiagent learning
- Deep learning methods for multiagent learning
- Transfer learning in multiagent settings
- Applications of multiagent learning to real-world systems
The purpose of this symposium is to bring together researchers from machine learning, control, neuroscience, robotics, and multi-agent learning/planning communities to discuss how to broaden the scope of multi-agent learning research and address the fundamental issues that hinder the applicability of multi-agent learning for solving complex real world problems.