A runtime monitoring framework to enforce invariants on reinforcement learning agents exploring complex environments

Piergiuseppe Mallozzi, Ezequiel Castellano, Patrizio Pelliccione, Gerardo Schneider, Kenji Tei

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

Abstract

Without prior knowledge of the environment, a software agent can learn to achieve a goal using machine learning. Model-free Reinforcement Learning (RL) can be used to make the agent explore the environment and learn to achieve its goal by trial and error. Discovering effective policies to achieve the goal in a complex environment is a major challenge for RL. Furthermore, in safety-critical applications, such as robotics, an unsafe action may cause catastrophic consequences in the agent or in the environment. In this paper, we present an approach that uses runtime monitoring to prevent the reinforcement learning agent to perform 'wrong' actions and to exploit prior knowledge to smartly explore the environment. Each monitor is de?ned by a property that we want to enforce to the agent and a context. The monitors are orchestrated by a meta-monitor that activates and deactivates them dynamically according to the context in which the agent is learning. We have evaluated our approach by training the agent in randomly generated learning environments. Our results show that our approach blocks the agent from performing dangerous and safety-critical actions in all the generated environments. Besides, our approach helps the agent to achieve its goal faster by providing feedback and shaping its reward during learning.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/ACM 2nd International Workshop on Robotics Software Engineering, RoSE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5-12
Number of pages8
ISBN (Electronic)9781728122496
DOIs
Publication statusPublished - 2019 May
Event2nd IEEE/ACM International Workshop on Robotics Software Engineering, RoSE 2019 - Montreal, Canada
Duration: 2019 May 27 → …

Publication series

NameProceedings - 2019 IEEE/ACM 2nd International Workshop on Robotics Software Engineering, RoSE 2019

Conference

Conference2nd IEEE/ACM International Workshop on Robotics Software Engineering, RoSE 2019
CountryCanada
CityMontreal
Period19/5/27 → …

    Fingerprint

Keywords

  • LTL invariants
  • Reinforcement learning
  • Reward shaping
  • Runtime monitoring

ASJC Scopus subject areas

  • Software
  • Control and Optimization

Cite this

Mallozzi, P., Castellano, E., Pelliccione, P., Schneider, G., & Tei, K. (2019). A runtime monitoring framework to enforce invariants on reinforcement learning agents exploring complex environments. In Proceedings - 2019 IEEE/ACM 2nd International Workshop on Robotics Software Engineering, RoSE 2019 (pp. 5-12). [8823721] (Proceedings - 2019 IEEE/ACM 2nd International Workshop on Robotics Software Engineering, RoSE 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RoSE.2019.00011