The Complexity of Decentralized Control of Markov Decision Processes
UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
Heuristic search value iteration for POMDPs
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Dynamic programming for partially observable stochastic games
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Indefinite-horizon POMDPs with action-based termination
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Decentralized control of cooperative systems: categorization and complexity analysis
Journal of Artificial Intelligence Research
Solving transition independent decentralized Markov decision processes
Journal of Artificial Intelligence Research
Memory-bounded dynamic programming for DEC-POMDPs
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Taming decentralized POMDPs: towards efficient policy computation for multiagent settings
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Point-based value iteration: an anytime algorithm for POMDPs
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Bounded policy iteration for decentralized POMDPs
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
An optimal best-first search algorithm for solving infinite horizon DEC-POMDPs
ECML'05 Proceedings of the 16th European conference on Machine Learning
Point-based policy generation for decentralized POMDPs
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Online planning for multi-agent systems with bounded communication
Artificial Intelligence
Reinforcement learning for decentralized planning under uncertainty
Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
Hi-index | 0.00 |
Coordination of multiple agents under uncertainty in the decentralized POMDP model is known to be NEXP-complete, even when the agents have a joint set of goals. Nevertheless, we show that the existence of goals can help develop effective planning algorithms. We examine an approach to model these problems as indefinite-horizon decentralized POMDPs, suitable for many practical problems that terminate after some unspecified number of steps. Our algorithm for solving these problems is optimal under some common assumptions -- that terminal actions exist for each agent and rewards for non-terminal actions are negative. We also propose an infinite-horizon approximation method that allows us to relax these assumptions while maintaining goal conditions. An optimality bound is developed for this sample-based approach and experimental results show that it is able to exploit the goal structure effectively. Compared with the state-of-the-art, our approach can solve larger problems and produce significantly better solutions.