Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2023

Abstract

Autonomous systems are often deployed in the open world where it is hard to obtain complete specifications of objectives and constraints. Operating based on an incomplete model can produce negative side effects (NSEs), which affect the safety and reliability of the system. We focus on mitigating NSEs in environments modeled as Markov decision processes (MDPs). First, we learn a model of NSEs using observed data that contains state-action trajectories and severity of associated NSEs. Unlike previous works that associate NSEs with state-action pairs, our framework associates NSEs with entire trajectories, which is more general and captures non-Markovian dependence on states and actions. Second, we learn finite state controllers (FSCs) that predict NSE severity for a given trajectory and generalize well to unseen data. Finally, we develop a constrained MDP model that uses information from the underlying MDP and the learned FSC for planning while avoiding NSEs. Our empirical evaluation demonstrates the effectiveness of our approach in learning and mitigating Markovian and non-Markovian NSEs.

Keywords

Constrained Markov decision process, Finite-state controllers, Incomplete model, Non-Markovian

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, February 7-14

Volume

37

First Page

15144

Last Page

15151

ISBN

9781577358800

Identifier

10.1609/aaai.v37i12.26767

Publisher

AAAI Press

City or Country

Washington

Additional URL

https://doi.org/10.1609/aaai.v37i12.26767

Download

Share

COinS