Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Multiagent teamwork: analyzing the optimality and complexity of key theories and models
Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 2
The Complexity of Decentralized Control of Markov Decision Processes
Mathematics of Operations Research
The complexity of multiagent systems: the price of silence
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Value-based observation compression for DEC-POMDPs
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Formal models and algorithms for decentralized decision making under uncertainty
Autonomous Agents and Multi-Agent Systems
Point-based incremental pruning heuristic for solving finite-horizon DEC-POMDPs
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Dynamic programming for partially observable stochastic games
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Point-based dynamic programming for DEC-POMDPs
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Policy iteration for decentralized control of Markov decision processes
Journal of Artificial Intelligence Research
Point-based backup for decentralized POMDPs: complexity and new algorithms
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
An investigation into mathematical programming for finite horizon decentralized POMDPs
Journal of Artificial Intelligence Research
An optimal best-first search algorithm for solving infinite horizon DEC-POMDPs
ECML'05 Proceedings of the 16th European conference on Machine Learning
Producing efficient error-bounded solutions for transition independent decentralized mdps
Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
Optimally solving dec-POMDPs as continuous-state MDPs
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Monte-Carlo expectation maximization for decentralized POMDPs
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Hi-index | 0.00 |
Over the past few years, attempts to scale up infinite-horizon DECPOMDPs are mainly due to approximate algorithms, but without the theoretical guarantees of their exact counterparts. In contrast, ε-optimal methods have only theoretical significance but are not efficient in practice. In this paper, we introduce an algorithmic frame-work (β-pi) that exploits the scalability of the former while preserving the theoretical properties of the latter. We build upon β-pi a family of approximate algorithms that can find (provably) errorbounded solutions in reasonable time. Among this family, h-pi uses a branch-and-bound search method that computes a near-optimal solution over distributions over histories experienced by the agents. These distributions often lie near structured, low-dimensional subspace embedded in the high-dimensional sufficient statistic. By planning only on this subspace, h-pi successfully solves all tested benchmarks, outperforming standard algorithms, both in solution time and policy quality.