Symbiotic Local Search for Small Decision Tree Policies in MDPs

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0198907" target="_blank" >RIV/00216305:26230/26:0198907 - isvavai.cz</a>

Result on the web

<a href="https://proceedings.mlr.press/v286/andriushchenko25a.html" target="_blank" >https://proceedings.mlr.press/v286/andriushchenko25a.html</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Symbiotic Local Search for Small Decision Tree Policies in MDPs

Original language description

We study decision making policies in Markov decision processes (MDPs). Two key performance indicators of such policies are their value and their interpretability. On the one hand, policies that optimize value can be efficiently computed via a plethora of standard methods. However, the representation of these policies may prevent their interpretability. On the other hand, policies with good interpretability, such as policies represented by a small decision tree, are computationally hard to obtain. This paper contributes a local search approach to find policies with good value, represented by small decision trees. Our local search symbiotically combines learning decision trees from value-optimal policies with symbolic approaches that optimize the size of the decision tree within a constrained neighborhood. Our empirical evaluation shows that this combination provides drastically smaller decision trees for MDPs that are significantly larger than what can be handled by optimal decision tree learners.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA23-06963S" target="_blank" >GA23-06963S: VESCAA: Verifiable and Efficient Synthesis of Controllers for Autonomous Agents</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence

ISBN

—

ISSN

—

e-ISSN

2640-3498

Number of pages

10

Pages from-to

132-142

Publisher name

ML Research Press

Place of publication

—

Event location

Rio de Janeiro

Event date

Jul 21, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001592914500007