Adversarially Robust Multitask Adaptive Control
This addresses robust control for collaborative systems in adversarial environments, but it is incremental as it builds on existing multitask and adaptive control methods.
The paper tackles the problem of multiple systems learning control policies under model uncertainty and adversarial corruption, showing that regret decreases inversely with the number of honest systems per cluster and remains stable under a bounded fraction of adversarial systems.
We study adversarially robust multitask adaptive linear quadratic control; a setting where multiple 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.