New algorithm improves decision-making models for conservation managers
Windowed A-K-MDP
Artificial Intelligence
Summary
Decision-making models called Markov decision processes (MDPs) help manage biodiversity but can be hard to understand. The authors found that a previous method for simplifying these models sometimes missed better solutions. They created a new method called Windowed A-K-MDP that looks more carefully at possible simplifications to avoid missing better options. Tests showed their new method was better or tied in almost all cases studied.
What this means in practice
- •For conservation managers: Generate simpler, more interpretable decision policies for managing biodiversity using improved MDP abstractions.
- •For environmental data analysts: Evaluate multiple candidate simplifications of decision models more comprehensively to identify better conservation strategies.
Authors
Xiangwen Yang, Frankie Cho, Iadine Chades
Abstract
Markov decision processes (MDPs) are used to support decision-making in conservation of biodiversity, but policies, even over small state spaces, can be difficult to interpret for conservation managers. K-MDP methods address this problem by building simpler MDPs with at most K abstract states. We show that the previously proposed A-K-MDP algorithm that relies on selecting a discretisation divisor using binary search can skip better abstract states. To fix this issue, we propose Windowed A-K-MDP, an algorithm that generates every distinct feasible partition induced within a declared divisor window and evaluates candidates until reaching the ideal value loss (J = 0) or exhausting the family of candidates. Across 33 K-MDP instances, Windowed improved 25 and tied 8.