ASP-Driven Emergency Planning for Norm Violations in Reinforcement Learning
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (14) , 14772-14780
Abstract
Reinforcement learning is a widely used approach for training an agent to maximize rewards in a given environment. Action policies learned with this technique see a broad range of applications in practical areas like games, healthcare, robotics, or autonomous driving. However, enforcing ethical behavior or norms based on deontic constraints that the agent should adhere to during policy execution remains a complex challenge. Especially constraints that emerge after the training can necessitate to redo policy learning, which can be costly and, more critically, time-intense. In order to mitigate this problem, we present a framework for policy fixing in case of a norm violation, which allows the agent to stay operational. Based on answer set programming (ASP), emergency plans are generated that exclude or minimize cost of norm violations by future actions in a horizon of interest. By combining and developing optimization techniques, efficient policy fixing under real-time constraints can be achieved.Keywords
This publication has 14 references indexed in Scilit:
- Cache-MAB: A reinforcement learning-based hybrid caching scheme in named data networksFuture Generation Computer Systems, 2023
- Answer Set Planning: A SurveyTheory and Practice of Logic Programming, 2022
- Recovery RL: Safe Reinforcement Learning With Learned Recovery ZonesIEEE Robotics and Automation Letters, 2021
- Deep Reinforcement Learning for Autonomous Driving: A SurveyIEEE Transactions on Intelligent Transportation Systems, 2021
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-playScience, 2018
- Multi-shot ASP solving with clingoTheory and Practice of Logic Programming, 2018
- Stream reasoning-based control of caching strategies in CCN routers2017
- Answer set programming at a glanceCommunications of the ACM, 2011
- Computational complexity of planning and approximate planning in the presence of incompletenessArtificial Intelligence, 2000
- Classical negation in logic programs and disjunctive databasesNew Generation Computing, 1991