Improved Memory-Bounded Dynamic Programming for Decentralized POMDPs

TL;DR

This paper enhances the Memory-Bounded Dynamic Programming algorithm for decentralized POMDPs by reducing complexity, providing error bounds, and demonstrating improved scalability through experiments on larger benchmarks.

Contribution

The paper generalizes and improves MBDP, reducing its complexity from exponential to polynomial in the number of observations, and provides theoretical and empirical validation.

Findings

Reduced complexity from exponential to polynomial in observations

Provided error bounds on solution quality

Scalable performance demonstrated on larger benchmarks

Abstract

Memory-Bounded Dynamic Programming (MBDP) has proved extremely effective in solving decentralized POMDPs with large horizons. We generalize the algorithm and improve its scalability by reducing the complexity with respect to the number of observations from exponential to polynomial. We derive error bounds on solution quality with respect to this new approximation and analyze the convergence behavior. To evaluate the effectiveness of the improvements, we introduce a new, larger benchmark problem. Experimental results show that despite the high complexity of decentralized POMDPs, scalable solution techniques such as MBDP perform surprisingly well.