Sequential Decision Making in Computational Sustainability via Adaptive Submodularity

Authors

  • Andreas Krause ETH Zurich
  • Daniel Golovin Google
  • Sarah Converse USGS Patuxent Wildlife Research Center

DOI:

https://doi.org/10.1609/aimag.v35i2.2526

Abstract

Many problems in computational sustainability require making a sequence of decisions in complex, uncertain environments. Such problems are generally notoriously difficult. In this article, we review the recently discovered notion of adaptive submodularity, an intuitive diminishing returns condition that generalizes the classical notion of submodular set functions to sequential decision problems. Problems exhibiting the adaptive submodularity property can be efficiently and provably near-optimally solved using simple myopic policies. We illustrate this concept in several case studies of interest in computational sustainability: First, we demonstrate how it can be used to efficiently plan for resolving uncertainty in adaptive management scenarios. Secondly, we show how it applies to dynamic conservation planning for protecting endangered species, a case study carried out in collaboration with the US Geological Survey and the US Fish and Wildlife Service.

Downloads

Published

2014-06-19

How to Cite

Krause, A., Golovin, D., & Converse, S. (2014). Sequential Decision Making in Computational Sustainability via Adaptive Submodularity. AI Magazine, 35(2), 8-18. https://doi.org/10.1609/aimag.v35i2.2526

Issue

Section

Articles