Policy gradient planning for environmental decision making with existing simulators

by Mark Crowley, David Poole
Proceedings of the National Conference on Artificial Intelligence ()


In environmental and natural resource planning domains actions are taken at a large number of locations over multiple time periods. These problems have enormous state and action spaces, spatial correlation between actions, uncertainty and complex utility models. We present an approach for modeling these planning problems as factored Markov decision processes. The reward model can contain local and global components as well as spatial constraints between locations. The transition dynamics can be provided by existing simulators developed by domain experts. We propose a landscape policy defined as the equilibrium distribution of a Markov chain built from many locally-parameterized policies. This policy is optimized using a policy gradient algorithm. Experiments using a forestry simulator demonstrate the algorithm's ability to devise policies for sustainable harvest planning of a forest. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.

Cite this document (BETA)

Available from Mark Crowley's profile on Mendeley.
Page 1
Page 2

Authors on Mendeley

Readership Statistics

12 Readers on Mendeley
by Discipline
by Academic Status
33% Researcher (at a non-Academic Institution)
33% Ph.D. Student
17% Other Professional
by Country
17% Canada
8% India

Sign up today - FREE

Mendeley saves you time finding and organizing research. Learn more

  • All your research in one place
  • Add and import papers easily
  • Access it anywhere, anytime

Start using Mendeley in seconds!

Sign up & Download

Already have an account? Sign in