Sequential decision making under uncertainty

Sequential decision making under uncertainty is a recurrent challenge in several related fields, including AI, control theory and statistics. To better understand randomness, Prof. Dirk Kroese and his team use Monte Carlo simulations.

Their research aims to develop theoretical and algorithmic tools to address the challenge of scaling-up existing methods to large complex environments, and explore their application in sustainable fishery management.

To approach these challenges, they use partially observable Markov decision processes (POMDPs) and Monte Carlo techniques.

POMDPs provide a general mathematical framework for sequential decision making under uncertainty. Both theoretical and algorithmic approaches will be applied to sustainable fishery management — an important problem for Australia and an ideal context for POMDPs. The project will advance research in artificial intelligence, dynamical systems, and fishery operations, and benefit the national economy.