Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

70141211281 · Jun 202019922001200920172026
48 results for regret control

A method to minimize regret in multi-agent control systems with adversarial disturbances.

problem Optimal control of dynamical systems with adversarial disturbances and multiple agents.
method Reduction from online convex optimization to a distributed algorithm for multi-agent control.
result The resulting distributed algorithm has low regret relative to the optimal precomputed joint policy.

We introduce a new algorithm for online linear-quadratic control in a known system subject to adversarial disturbances. Existing regret bounds for this setting scale as T\sqrt{T} unless strong stochastic assumptions are imposed on the disturbance process. We give the first algorithm with logarithmic regret for arbitra…

2020-02-29abs ↗pdf ↗

We study the problem of regret minimization in partially observable linear quadratic control systems when the model dynamics are unknown a priori. We propose ExpCommit, an explore-then-commit algorithm that learns the model Markov parameters and then follows the principle of optimism in the face of uncertainty to desig…

2020-01-31abs ↗pdf ↗

TSAC achieves optimal frequentist regret in adaptive control of LQRs.

problem Adaptive control of stabilizable linear-quadratic regulators with unknown dynamics.
method Thompson Sampling (TS) for adaptive control of LQRs, with a novel early exploration strategy.
result Achieves ildeO(T) ilde O(\sqrt{T}) regret, optimal for multidimensional systems.

We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed states, known as non-stochastic control. We introduce a controller parametrization based on the denoised observations, and prove that apply…

2020-01-25abs ↗pdf ↗

We consider the exploration-exploitation tradeoff in linear quadratic (LQ) control problems, where the state dynamics is linear and the cost function is quadratic in states and controls. We analyze the regret of Thompson sampling (TS) (a.k.a. posterior-sampling for reinforcement learning) in the frequentist setting, i.…

2017-03-27abs ↗pdf ↗

New algorithm achieves optimal regret in non-stochastic control, showing stochasticity is not beneficial.

problem Achieving optimal control in non-stochastic systems with adversarial noise.
method Novel online Newton step algorithm adapted to adversarial disturbances, using policy regret bounds.
result Optimal O~(T)\widetilde{\mathcal{O}}(\sqrt{T}) regret achieved in unknown dynamics, poly(logT)\mathrm{poly}(\log T) regret in known dynamics.

PCGS-TF uses a Transformer to adaptively control expert switching in non-stationary environments.

problem Static regret is insufficient for strictly online prediction in non-stationary settings.
method Policy-Controlled Generalized Share (PCGS) with a Transformer as an update controller.
result PCGS-TF achieves the lowest dynamic regret in non-stationary families and expert pools.

Safe RL in linear systems achieves T\sqrt{T}-regret.

problem Efficiently learning in safety-constrained online reinforcement learning.
method Study of linear quadratic regulator with safety constraints.
result First safe algorithm with ildeOT(T) ilde{O}_T(\sqrt{T})-regret.

The study sets limits on how well systems can be controlled adaptively.

problem Learning to control unknown linear Gaussian systems with quadratic costs.
method Combining ideas from experiment design, estimation theory, and perturbation bounds of information matrices.
result Regret lower bounds of the order of T\sqrt{T} in the time horizon TT accurately capture control-theoretic parameters.

AdaptOn achieves logarithmic regret in adaptive control of unknown partially observable linear systems.

problem Adaptive control in partially observable linear dynamical systems.
method AdaptOn algorithm that estimates system dynamics through online learning and gradient descent.
result AdaptOn achieves a logarithmic regret bound of polylog(T) after T steps.

GP-PSRL achieves sublinear regret for continuous control with unbounded state space.

problem Analyzing regret bounds for GP-PSRL in continuous control with unbounded state space.
method Recursive application of Borell-Tsirelson-Ibragimov-Sudakov inequality and chaining method.
result Sublinear regret bound of O~(HγTT)\widetilde{\mathcal{O}}(H\sqrt{γ_TT}) for GP-PSRL.

The paper improves regret bounds for admission control in queueing systems.

problem Improving regret bounds for admission control in queueing systems.
method Proposes an algorithm inspired by UCRL2 and uses problem structure to bound regret.
result Proves an upper bound on the expected total regret of O(SlogT+mTlogT)O(S\log T + \sqrt{mT \log T}).

We study optimal regret bounds for control in linear dynamical systems under adversarially changing strongly convex cost functions, given the knowledge of transition dynamics. This includes several well studied and fundamental frameworks such as the Kalman filter and the linear quadratic regulator. State of the art met…

2019-09-11abs ↗pdf ↗

Optimal algorithm for LQR control with improved regret bound.

problem Nonstochastic control with quadratic losses (LQR control).
method Online algorithm with optimal dynamic regret of ildeO(extmax{n1/3TV(M1:n)2/3,1}) ilde{O}( ext{max}\{n^{1/3} \mathcal{TV}(M_{1:n})^{2/3}, 1\}).
result Improves the best known rate of ildeO(n(TV(M1:n)+1)) ilde{O}(\sqrt{n (\mathcal{TV}(M_{1:n})+1)} ) for general convex losses.

Paper tackles online control of linear systems with unbounded noise.

problem Online control of linear systems under unbounded noise with unknown convex cost functions.
method Developed an algorithm achieving ildeO(T) ilde{O}(\sqrt{T}) high-probability regret under unbounded noise, and established O(mpoly(logT)) O({ m poly} (\log T)) regret bound for strongly convex costs and sub-Gaussian noise.
result Achieved ildeO(T) ilde{O}(\sqrt{T}) high-probability regret under unbounded noise, and O(mpoly(logT)) O({ m poly} (\log T)) regret bound for specific noise and cost conditions.

Logarithmic regret achieved in continuous-time linear-quadratic reinforcement learning.

problem Optimizing control actions in unknown continuous-time systems over a finite time horizon.
method Least-squares algorithm based on continuous-time observations and controls, with perturbation analysis and parameter estimation error analysis.
result Logarithmic regret bound of order O((lnM)(lnlnM))O((\ln M)(\ln\ln M)).

Optimal control in changing systems without strong convexity assumptions.

problem Adversarial changes in convex costs for unknown linear systems.
method Non-convex lower confidence bounds and computationally-efficient regret minimization.
result Achieves T\smash{\sqrt{T}}-regret rate, optimal compared to best stabilizing controller.

Study shows certainty equivalent policy minimizes regret in continuous-time systems.

problem Minimizing regret in continuous-time stochastic linear-quadratic systems.
method Theoretical analysis of randomized certainty equivalent policy.
result Establishes square-root of time regret bounds and linear scaling with parameters.

Study shows how to learn optimal policies quickly in stochastic control problems.

problem Learning optimal policies in large, continuous state and action spaces with limited data.
method Analyzes three geometric exponents to quantify fast policy regret convergence.
result Shows that fast policy regret convergence is induced by specific geometric structures.

LqgOpt learns optimal control in unknown LQG systems with minimal regret.

problem Adaptive control in partially observable linear quadratic Gaussian systems with unknown dynamics.
method Optimism in the face of uncertainty, predictor state evolution, closed-loop system identification, confidence bounds.
result Proves a regret upper bound of ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) for LQG systems.

We consider the problem of controlling an unknown linear dynamical system in the presence of (nonstochastic) adversarial perturbations and adversarial convex loss functions. In contrast to classical control, the a priori determination of an optimal controller here is hindered by the latter's dependence on the yet unkno…

2019-11-27abs ↗pdf ↗

Algorithm minimizes control regret for non-stationary LQR systems.

problem Control of non-stationary LQR systems with unknown dynamics.
method Adaptive non-stationarity detection and OLS estimator with small bias.
result Achieves optimal dynamic regret of $ ilde{\mathcal{O}}\left(V_T^{2/5}T^{3/5} ight)$.

This paper tackles adaptive control of unknown Markov jump systems with sample complexity and regret bounds.

problem Adaptive control of unknown Markov jump systems with changing dynamics.
method Identification-based adaptive control using a system identification algorithm and certainty equivalent control.
result The proposed adaptive control scheme achieves O(T)\mathcal{O}(\sqrt{T}) regret, improving to O(polylog(T))\mathcal{O}(polylog(T)) with partial knowledge.

New Q-learning algorithms reduce regret in inventory control problems.

problem Efficiently learning optimal policies in inventory control problems with limited feedback.
method Proposed Elimination-Based Half-Q-Learning (HQL) and Full-Q-Learning (FQL) algorithms with theoretical regret bounds.
result HQL incurs ildeO(H3T) ilde{\mathcal{O}}(H^3\sqrt{ T}) regret, FQL incurs ildeO(H2T) ilde{\mathcal{O}}(H^2\sqrt{ T}) regret, independent of state and action space sizes.

New bounds for adaptive control in high dimensions without fixed state space.

problem Adaptive control of linear systems in high or infinite dimensions.
method Novel perturbation bound for certainty equivalence, scaling with prediction error.
result First regret bounds for LQR in infinite dimensional systems, independent of ambient dimension.

We consider the problem of online adaptive control of the linear quadratic regulator, where the true system parameters are unknown. We prove new upper and lower bounds demonstrating that the optimal regret scales as Θ~(du2dxT)\widetildeΘ({\sqrt{d_{\mathbf{u}}^2 d_{\mathbf{x}} T}}), where TT is the number of time steps, $d_{\m…

2020-01-27abs ↗pdf ↗

New algorithm achieves both static and dynamic regret optimally against an oblivious adversary for deterministic losses.

problem Achieving optimal static and dynamic regret simultaneously in adversarial bandits.
method Extends impossibility result to deterministic losses, uses negative static regret and Blackwell approachability.
result First algorithm achieving optimal static and dynamic regret simultaneously against an oblivious adversary.

SA algorithms control dynamic regret in non-stationary settings with strong convexity or exp-concavity.

problem Non-stationary Online Convex Optimization with dynamic regret control.
method Strongly Adaptive (SA) algorithms view dynamic regret as path variation of the comparator sequence.
result SA algorithms achieve ildeO(TVTlogT) ilde O(\sqrt{TV_T} \vee \log T) and ildeO(dTVTdlogT) ilde O(\sqrt{dTV_T} \vee d\log T) dynamic regret for strongly convex and exp-concave losses, respectively.