Open Access. Powered by Scholars. Published by Universities.®

Operations Research, Systems Engineering and Industrial Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Series

Artificial Intelligence and Robotics

Maximum principle

Articles 1 - 2 of 2

Full-Text Articles in Operations Research, Systems Engineering and Industrial Engineering

Dual Formulations For Optimizing Dec-Pomdp Controllers, Akshat Kumar, Hala Mostafa, Shlomo Zilberstein Jun 2016

Dual Formulations For Optimizing Dec-Pomdp Controllers, Akshat Kumar, Hala Mostafa, Shlomo Zilberstein

Research Collection School Of Information Systems

Decentralized POMDP is an expressive model for multi-agent planning. Finite-state controllers (FSCs)---often used to represent policies for infinite-horizon problems---offer a compact, simple-to-execute policy representation. We exploit novel connections between optimizing decentralized FSCs and the dual linear program for MDPs. Consequently, we describe a dual mixed integer linear program (MIP) for optimizing deterministic FSCs. We exploit the Dec-POMDP structure to devise a compact MIP and formulate constraints that result in policies executable in partially-observable decentralized settings. We show analytically that the dual formulation can also be exploited within the expectation maximization (EM) framework to optimize stochastic FSCs. The resulting EM ...


Shortest Path Based Decision Making Using Probabilistic Inference, Akshat Kumar Feb 2016

Shortest Path Based Decision Making Using Probabilistic Inference, Akshat Kumar

Research Collection School Of Information Systems

We present a new perspective on the classical shortest path routing (SPR) problem in graphs. We show that the SPR problem can be recast to that of probabilistic inference in a mixture of simple Bayesian networks. Maximizing the likelihood in this mixture becomes equivalent to solving the SPR problem. We develop the well known Expectation-Maximization (EM) algorithm for the SPR problem that maximizes the likelihood, and show that it does not get stuck in a locally optimal solution. Using the same probabilistic framework, we then address an NP-Hard network design problem where the goal is to repair a network of ...