Regret-optimal control in dynamic environments

• URL: http://arxiv.org/abs/2010.10473v2
• Date: Mon, 1 Feb 2021 22:29:37 GMT
• Title: Regret-optimal control in dynamic environments
• Authors: Gautam Goel, Babak Hassibi
• Abstract summary: We focus on the problem of designing an online controller which minimizes regret against the best dynamic sequence of control actions selected in hindsight. We derive the state-space structure of the regret-optimal controller via a novel reduction to $H_infty$ control. We present numerical experiments which show that our regret-optimal controller interpolates between the performance of the $H_infty$-optimal controllers across and adversarial environments.
• Score: 39.76359052907755
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider control in linear time-varying dynamical systems from the perspective of regret minimization. Unlike most prior work in this area, we focus on the problem of designing an online controller which minimizes regret against the best dynamic sequence of control actions selected in hindsight (dynamic regret), instead of the best fixed controller in some specific class of controllers (static regret). This formulation is attractive when the environment changes over time and no single controller achieves good performance over the entire time horizon. We derive the state-space structure of the regret-optimal controller via a novel reduction to $H_{\infty}$ control and present a tight data-dependent bound on its regret in terms of the energy of the disturbance. Our results easily extend to the model-predictive setting where the controller can anticipate future disturbances and to settings where the controller only affects the system dynamics after a fixed delay. We present numerical experiments which show that our regret-optimal controller interpolates between the performance of the $H_2$-optimal and $H_{\infty}$-optimal controllers across stochastic and adversarial environments.

Related papers

• On Controller Tuning with Time-Varying Bayesian Optimization [74.57758188038375]
  We will use time-varying optimization (TVBO) to tune controllers online in changing environments using appropriate prior knowledge on the control objective and its changes. We propose a novel TVBO strategy using Uncertainty-Injection (UI), which incorporates the assumption of incremental and lasting changes. Our model outperforms the state-of-the-art method in TVBO, exhibiting reduced regret and fewer unstable parameter configurations.
  arXiv  Detail & Related papers  (2022-07-22T14:54:13Z)
• Competitive Control [52.28457815067461]
  We focus on designing an online controller which competes against a clairvoyant offline optimal controller. A natural performance metric in this setting is competitive ratio, which is the ratio between the cost incurred by the online controller and the cost incurred by the offline optimal controller.
  arXiv  Detail & Related papers  (2021-07-28T22:26:27Z)
• Regret-optimal Estimation and Control [52.28457815067461]
  We show that the regret-optimal estimator and regret-optimal controller can be derived in state-space form. We propose regret-optimal analogs of Model-Predictive Control (MPC) and the Extended KalmanFilter (EKF) for systems with nonlinear dynamics.
  arXiv  Detail & Related papers  (2021-06-22T23:14:21Z)
• Regret-Optimal LQR Control [37.99652162611661]
  We find a causal controller that minimizes the worst-case regret over all bounded energy disturbances. We derive explicit formulas for the optimal regret and for the regret-optimal controller for the state-space setting. The regret-optimal controller presents itself as a viable option for control systems design.
  arXiv  Detail & Related papers  (2021-05-04T01:51:00Z)
• Regret-optimal measurement-feedback control [39.76359052907755]
  We consider measurement-feedback control in linear dynamical systems from the perspective of regret. We show that in the measurement-feedback setting, unlike in the full information setting, there is no single offline controller which outperforms every other offline controller on every disturbance. We show that the corresponding regret-optimal online controller can be found via a novel reduction to the classical Nehari problem and present a tight data-dependent bound on its regret.
  arXiv  Detail & Related papers  (2020-11-24T01:36:48Z)
• Improper Learning for Non-Stochastic Control [78.65807250350755]
  We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed states. Applying online descent to this parametrization yields a new controller which attains sublinear regret vs. a large class of closed-loop policies. Our bounds are the first in the non-stochastic control setting that compete with emphall stabilizing linear dynamical controllers.
  arXiv  Detail & Related papers  (2020-01-25T02:12:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.