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

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

研究成果: Conference contribution

抜粋

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.

元の言語English
ホスト出版物のタイトルProceedings - 2019 IEEE/ACM 2nd International Workshop on Robotics Software Engineering, RoSE 2019
出版者Institute of Electrical and Electronics Engineers Inc.
ページ5-12
ページ数8
ISBN(電子版)9781728122496
DOI
出版物ステータスPublished - 2019 5
イベント2nd IEEE/ACM International Workshop on Robotics Software Engineering, RoSE 2019 - Montreal, Canada
継続期間: 2019 5 27 → …

出版物シリーズ

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

Conference

Conference2nd IEEE/ACM International Workshop on Robotics Software Engineering, RoSE 2019
Canada
Montreal
期間19/5/27 → …

ASJC Scopus subject areas

  • Software
  • Control and Optimization

フィンガープリント A runtime monitoring framework to enforce invariants on reinforcement learning agents exploring complex environments' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    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. : 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