Adversarially Robust Multitask Adaptive Control

Kasra Fallah, Leonardo Felipe Toso, James Anderson
Proceedings of The 8th Annual Learning for Dynamics and Control Conference, PMLR 331:1818-1856, 2026.

Abstract

We study adversarially robust multitask adaptive linear quadratic control; a setting where multiple (potentially different) systems collaboratively learn control policies under model uncertainty and adversarial corruption. We propose a clustered multitask approach that integrates clustering and system identification with resilient aggregation to mitigate corrupted model updates. Our analysis characterizes how clustering accuracy, intra-cluster heterogeneity, and adversarial behavior affect the expected regret of certainty-equivalent (CE) control across LQR tasks. We establish non-asymptotic bounds demonstrating that the regret decreases inversely with the number of honest systems per cluster and that this reduction is preserved under a bounded fraction of adversarial systems within each cluster.

Cite this Paper

BibTeX
@InProceedings{pmlr-v331-fallah26a, title = {Adversarially Robust Multitask Adaptive Control}, author = {Fallah, Kasra and Toso, Leonardo Felipe and Anderson, James}, booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference}, pages = {1818--1856}, year = {2026}, editor = {Sukhatme, Gaurav and Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, volume = {331}, series = {Proceedings of Machine Learning Research}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v331/main/assets/fallah26a/fallah26a.pdf}, url = {https://proceedings.mlr.press/v331/fallah26a.html}, abstract = {We study adversarially robust multitask adaptive linear quadratic control; a setting where multiple (potentially different) systems collaboratively learn control policies under model uncertainty and adversarial corruption. We propose a clustered multitask approach that integrates clustering and system identification with resilient aggregation to mitigate corrupted model updates. Our analysis characterizes how clustering accuracy, intra-cluster heterogeneity, and adversarial behavior affect the expected regret of certainty-equivalent (CE) control across LQR tasks. We establish non-asymptotic bounds demonstrating that the regret decreases inversely with the number of honest systems per cluster and that this reduction is preserved under a bounded fraction of adversarial systems within each cluster.} }
Endnote
%0 Conference Paper %T Adversarially Robust Multitask Adaptive Control %A Kasra Fallah %A Leonardo Felipe Toso %A James Anderson %B Proceedings of The 8th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2026 %E Gaurav Sukhatme %E Lars Lindemann %E Stephen Tu %E Adam Wierman %E Nikolay Atanasov %F pmlr-v331-fallah26a %I PMLR %P 1818--1856 %U https://proceedings.mlr.press/v331/fallah26a.html %V 331 %X We study adversarially robust multitask adaptive linear quadratic control; a setting where multiple (potentially different) systems collaboratively learn control policies under model uncertainty and adversarial corruption. We propose a clustered multitask approach that integrates clustering and system identification with resilient aggregation to mitigate corrupted model updates. Our analysis characterizes how clustering accuracy, intra-cluster heterogeneity, and adversarial behavior affect the expected regret of certainty-equivalent (CE) control across LQR tasks. We establish non-asymptotic bounds demonstrating that the regret decreases inversely with the number of honest systems per cluster and that this reduction is preserved under a bounded fraction of adversarial systems within each cluster.
APA
Fallah, K., Toso, L.F. & Anderson, J.. (2026). Adversarially Robust Multitask Adaptive Control. Proceedings of The 8th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 331:1818-1856 Available from https://proceedings.mlr.press/v331/fallah26a.html.

Related Material