Verifiable and interpretable reinforcement learning through program synthesis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

We study the problem of generating interpretable and verifiable policies for Reinforcement Learning (RL). Unlike the popular Deep Reinforcement Learning (DRL) paradigm, in which the policy is represented by a neural network, the aim of this work is to find policies that can be represented in high-level programming languages. Such programmatic policies have several benefits, including being more easily interpreted than neural networks, and being amenable to verification by scalable symbolic methods. The generation methods for programmatic policies also provide a mechanism for systematically using domain knowledge for guiding the policy search. The interpretability and verifiability of these policies provides the opportunity to deploy RL based solutions in safety critical environments. This thesis draws on, and extends, work from both the machine learning and formal methods communities.

Original languageEnglish (US)
Title of host publication33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
PublisherAAAI press
Pages9902-9903
Number of pages2
ISBN (Electronic)9781577358091
StatePublished - 2019
Event33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019 - Honolulu, United States
Duration: Jan 27 2019Feb 1 2019

Publication series

Name33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019

Conference

Conference33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
Country/TerritoryUnited States
CityHonolulu
Period1/27/192/1/19

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Verifiable and interpretable reinforcement learning through program synthesis'. Together they form a unique fingerprint.

Cite this