Pointwise-in-Time Diagnostics for Reinforcement Learning During Training and Runtime
Abstract
Explainable AI Planning (XAIP), a subfield of xAI, offers a variety of methods to interpret the behavior of autonomous systems. A recent “pointwise-in-time” explanation method, called Rule Status Assessment (RSA), characterizes an agent’s behavior at individual time steps in a trajectory using linear temporal logic (LTL) rules. In this work, RSA is applied for the first time in a reinforcement learning (RL) context. We first demonstrate RSA diagnostics as a substantial supplement to the basic RL reward curve, tracking whether and when specified subtasks are accomplished. We then introduce a novel “Interactive RSA” which provides the user with detailed diagnostic information automatically at any desired point in a trajectory. We apply RSA to an advanced agent at runtime and show that RSA and its novel interactive variant constitute a promising step towards explainable RL.
Cite
Text
Brindise et al. "Pointwise-in-Time Diagnostics for Reinforcement Learning During Training and Runtime." Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024.Markdown
[Brindise et al. "Pointwise-in-Time Diagnostics for Reinforcement Learning During Training and Runtime." Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024.](https://mlanthology.org/l4dc/2024/brindise2024l4dc-pointwiseintime/)BibTeX
@inproceedings{brindise2024l4dc-pointwiseintime,
title = {{Pointwise-in-Time Diagnostics for Reinforcement Learning During Training and Runtime}},
author = {Brindise, Noel and Moreno, Andres Posada and Langbort, Cedric and Trimpe, Sebastian},
booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference},
year = {2024},
pages = {694-706},
volume = {242},
url = {https://mlanthology.org/l4dc/2024/brindise2024l4dc-pointwiseintime/}
}