A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces

Omar Darwiche Domingues, Pierre Menard, Matteo Pirotta, Emilie Kaufmann, Michal Valko
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:3538-3546, 2021.

Abstract

In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric. Using a non-parametric model of the MDP built with time-dependent kernels, we prove a regret bound that scales with the covering dimension of the state-action space and the total variation of the MDP with time, which quantifies its level of non-stationarity. Our method generalizes previous approaches based on sliding windows and exponential discounting used to handle changing environments. We further propose a practical implementation of KeRNS, we analyze its regret and validate it experimentally.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-darwiche-domingues21a, title = { A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces }, author = {Darwiche Domingues, Omar and Menard, Pierre and Pirotta, Matteo and Kaufmann, Emilie and Valko, Michal}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {3538--3546}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/darwiche-domingues21a/darwiche-domingues21a.pdf}, url = {https://proceedings.mlr.press/v130/darwiche-domingues21a.html}, abstract = { In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric. Using a non-parametric model of the MDP built with time-dependent kernels, we prove a regret bound that scales with the covering dimension of the state-action space and the total variation of the MDP with time, which quantifies its level of non-stationarity. Our method generalizes previous approaches based on sliding windows and exponential discounting used to handle changing environments. We further propose a practical implementation of KeRNS, we analyze its regret and validate it experimentally. } }
Endnote
%0 Conference Paper %T A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces %A Omar Darwiche Domingues %A Pierre Menard %A Matteo Pirotta %A Emilie Kaufmann %A Michal Valko %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-darwiche-domingues21a %I PMLR %P 3538--3546 %U https://proceedings.mlr.press/v130/darwiche-domingues21a.html %V 130 %X In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric. Using a non-parametric model of the MDP built with time-dependent kernels, we prove a regret bound that scales with the covering dimension of the state-action space and the total variation of the MDP with time, which quantifies its level of non-stationarity. Our method generalizes previous approaches based on sliding windows and exponential discounting used to handle changing environments. We further propose a practical implementation of KeRNS, we analyze its regret and validate it experimentally.
APA
Darwiche Domingues, O., Menard, P., Pirotta, M., Kaufmann, E. & Valko, M.. (2021). A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:3538-3546 Available from https://proceedings.mlr.press/v130/darwiche-domingues21a.html.

Related Material