A runtime monitoring framework to enforce invariants on reinforcement learning agents exploring complex environments
Paper in proceeding, 2019

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.

Reinforcement learning

LTL invariants

Reward shaping

Runtime monitoring

Author

Piergiuseppe Mallozzi

Chalmers, Computer Science and Engineering (Chalmers), Software Engineering (Chalmers)

Ezequiel Castellano

The Graduate University for Advanced Studies (SOKENDAI)

Patrizio Pelliccione

University of L'Aquila

Chalmers, Computer Science and Engineering (Chalmers), Software Engineering (Chalmers)

Gerardo Schneider

Chalmers, Computer Science and Engineering (Chalmers), Formal methods

Kenji Tei

Waseda University

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

5-12 8823721
978-1-7281-2249-6 (ISBN)

2nd IEEE/ACM International Workshop on Robotics Software Engineering, RoSE 2019
Montreal, Canada,

Subject Categories

Learning

Robotics

Computer Science

DOI

10.1109/RoSE.2019.00011

More information

Latest update

1/3/2024 9