Solving very large weakly coupled Markov decision processes
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
How to dynamically merge Markov decision processes
NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Regret bounds for prediction problems
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
Prediction, Learning, and Games
Prediction, Learning, and Games
Combinatorial resource scheduling for multiagent MDPs
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
No-regret learning and a mechanism for distributed multiagent planning
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
The power of sequential single-item auctions for agent coordination
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Distributed model shaping for scaling to decentralized POMDPs with hundreds of agents
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 3
Decentralized decision support for an agent population in dynamic and uncertain domains
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 3
Distributed planning in hierarchical factored MDPs
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
PEGASUS: a policy search method for large MDPs and POMDPs
UAI'00 Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence
Hi-index | 0.00 |
Multi-agent planning is a well-studied problem with various applications including disaster rescue, urban transportation and logistics, both for autonomous agents and for decision support to humans. Due to computational constraints, existing research typically focuses on one of two scenarios: unstructured domains with many agents where we are content with heuristic solutions, or domains with small numbers of agents or special structure where we can provide provably near-optimal solutions. By contrast, in this paper, we focus on providing provably near-optimal solutions for domains with large numbers of agents, by exploiting a common domain-general property: if individual agents each have limited influence on the overall solution quality, then we can take advantage of randomization and the resulting statistical concentration to show that each agent can safely plan based only on the average behavior of the other agents. To that end, we make two key contributions: (a) an algorithm, based on Lagrangian relaxation and randomized rounding, for solving multi-agent planning problems represented as large mixed-integer programs, (b) a proof of convergence of our algorithm to a near-optimal solution. We demonstrate the scalability of our approach with a large-scale illustrative theme park crowd management problem.