International Workshop on Multiagent Learning: Theory and Applications

In the last two decades, machine learning techniques have been explored extensively as a vital component to address challenges in multi-agent systems, which is known as Multiagent Learning. For example, many application domains are envisioned in which teams of software agents or robots learn to cooperate amongst each other and with human beings to achieve global objectives. Multiagent learning may also be essential in many non-cooperative scenarios such as negotiation and auction, where classical game-theoretic solutions are either infeasible or inappropriate. Multiagent learning is an active field of research that deals with the problem of how agents can learn and adapt effectively in non-stationary environments where other coexisting agents are simultaneously learning and adapting. This is a fertile area of research that seems ripe for progress and we have witnessed numerous significant theoretical and practical developments in the last two decades. Large bodies of multiagent learning techniques have been developed to address the question of learning towards optimal solutions (e.g., Nash equilibrium, Pareto optimality and social optimality) against different types of partners (e.g., self-play, certain types of selfish players). This workshop focuses on theory and practice in multi-agent learning. We would like to create a forum to discuss interesting results both theoretically and empirically related with multiagent learning. The goal of this workshop aims to bring together diverse viewpoints in multiagent leaerning in an attempt to consolidate the common ground, identify new lines of directions, sharing insights into recent results and common challenges, and ultimately promote the rapid advance of multiagent learning research community.