Distributed Artificial Intelligence: Second International Conference, DAI 2020, Nanjing, China, October 24–27, 2020, Proceedings

When intelligent systems act as a team—or compete without a central decision-maker—how should they learn, coordinate, and choose their next move? Distributed Artificial Intelligence brings together refereed research from DAI 2020 on these questions, with contributions that connect foundational methods to problems in games, robotics, and automated systems.

Edited by Matthew E. Taylor, Yang Yu, Edith Elkind, and Yang Gao, this proceedings volume ranges across multi-agent learning, distributed systems, computational game theory, and reinforcement learning. Its research papers offer a focused snapshot of the challenges and approaches shaping distributed AI.

Where agents learn and make decisions together

Several contributions investigate learning when agents must operate in shared or decentralized environments. Topics include hierarchical reinforcement learning, continuous control, decentralized multi-agent control, cooperative Markov games, and exploration. For readers studying multi-agent systems, the collection brings different learning problems and methods into one research-oriented volume.

Strategy, coordination, and real-world settings

Game-theoretic work includes an algorithm for finding Nash equilibria in multiplayer stochastic games, illustrated with a naval strategic-planning scenario. Other papers address multi-agent coordination and collision-free navigation. The collection also explores an applied industrial setting: managing batteries in automated warehouses through deep reinforcement learning.

A cross-section of distributed AI research

Rather than following a single textbook-style progression, the proceedings gather nine papers across complementary areas. That breadth makes the volume useful for seeing how distributed artificial intelligence connects mathematical questions about strategy with practical concerns such as control, navigation, and system coordination.

Who may find this volume relevant?

Researchers, graduate students, and practitioners working in artificial intelligence, autonomous agents, multi-agent systems, reinforcement learning, robotics, or computational game theory may find these proceedings relevant to their work and reading. 📚