Optimizing Memory-Bounded Controllers for Decentralized POMDPs
This addresses decision-making under uncertainty for multi-agent systems, but it is incremental as it builds on existing nonlinear optimization techniques.
The paper tackles the problem of solving infinite-horizon decentralized POMDPs by optimizing memory-bounded stochastic finite state controllers using a nonlinear programming formulation, resulting in higher quality controllers than state-of-the-art methods and improved solutions with a correlation device.
We present a memory-bounded optimization approach for solving infinite-horizon decentralized POMDPs. Policies for each agent are represented by stochastic finite state controllers. We formulate the problem of optimizing these policies as a nonlinear program, leveraging powerful existing nonlinear optimization techniques for solving the problem. While existing solvers only guarantee locally optimal solutions, we show that our formulation produces higher quality controllers than the state-of-the-art approach. We also incorporate a shared source of randomness in the form of a correlation device to further increase solution quality with only a limited increase in space and time. Our experimental results show that nonlinear optimization can be used to provide high quality, concise solutions to decentralized decision problems under uncertainty.