arXiv research

Algorithm minimizes control regret for non-stationary LQR systems.

Safe RL-based vibration control using LQR guidance.

Optimal algorithm for LQR control with improved regret bound.

Efficiently solves exploration-exploitation in LQR using Lagrangian relaxation.

The paper sets bounds on how much regret is unavoidable in adaptive LQR with unknown B-matrix.

TSAC achieves optimal frequentist regret in adaptive control of LQRs.

New insights into RL efficiency from managing time discretization.

New model-free algorithm achieves similar LQR regret guarantees.

Finding optimal feedback controllers for nonlinear dynamic systems from data is hard. Recently, Bayesian optimization (BO) has been proposed as a powerful framework for direct controller tuning from experimental trials. For selecting the next query point and finding the global optimum, BO relies on a probabilistic desc…

New algorithm learns LQR with $O(\sqrt{T})$ regret using Langevin dynamics and excitation.

Policy gradient methods converge for LQR problems with noisy state dynamics.

Global convergence proved for multi-agent LQRs with hierarchical actor-critic.

Optimal trading strategy using LQR framework with price mean-reversion.

This manuscript surveys reinforcement learning from the perspective of optimization and control with a focus on continuous control applications. It surveys the general formulation, terminology, and typical experimental implementations of reinforcement learning and reviews competing solution paradigms. In order to compa…

We study the sample complexity of approximate policy iteration (PI) for the Linear Quadratic Regulator (LQR), building on a recent line of work using LQR as a testbed to understand the limits of reinforcement learning (RL) algorithms on continuous control tasks. Our analysis quantifies the tension between policy improv…

The linear quadratic regulator (LQR) problem has reemerged as an important theoretical benchmark for reinforcement learning-based control of complex dynamical systems with continuous state and action spaces. In contrast with nearly all recent work in this area, we consider multiplicative noise models, which are increas…

The study examines when MAML's objective has a benign landscape.

Paper proposes a COP model for Algo trading using LQR.

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that provides high…

We describe an optimal adversarial attack formulation against autoregressive time series forecast using Linear Quadratic Regulator (LQR). In this threat model, the environment evolves according to a dynamical system; an autoregressive model observes the current environment state and predicts its future values; an attac…

The paper presents a model-free method for stabilizing unknown control systems.

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

Reinforcement learning (RL) has been successfully used to solve many continuous control tasks. Despite its impressive results however, fundamental questions regarding the sample complexity of RL on continuous problems remain open. We study the performance of RL in this setting by considering the behavior of the Least-S…

RichID learns optimal control policies from nonlinear observations.

New definition resolves ambiguity in non-stationary bandit classification.

SmoothFBO tackles non-stationary functional bilevel optimization.

Proposes a new algorithm for non-stationary bandits.

Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.

Study incentivizes exploration in non-stationary MAB with compensation.

New algorithm tackles non-stationary reinforcement learning with general function approximation.

Proposes a method to forecast non-stationary time series.

New definitions of ESP for quantum reservoir computing handle non-stationary systems.

Study combines VICReg and TNC for better encoding of non-stationary seismic signals.

We propose non-stationary spectral kernels for Gaussian process regression. We propose to model the spectral density of a non-stationary kernel function as a mixture of input-dependent Gaussian process frequency density surfaces. We solve the generalised Fourier transform with such a model, and present a family of non-…

Algorithm adapts to non-stationary rewards without prior knowledge.

This paper develops the first method for the exact simulation of reflected Brownian motion (RBM) with non-stationary drift and infinitesimal variance. The running time of generating exact samples of non-stationary RBM at any time $t$ is uniformly bounded by $\mathcal{O}(1/\barγ^2)$ where $\barγ$ is the average drift of…

Unified review of methods for inferring non-stationary process parameters.

Unified approach for non-stationary and clustered bandits.

This paper studies how gradient descent in control systems can perform well on unseen data.

Non-stationarity appears in many online applications such as web search and advertising. In this paper, we study the online learning to rank problem in a non-stationary environment where user preferences change abruptly at an unknown moment in time. We consider the problem of identifying the K most attractive items and…

In this paper, we obtain the finite-horizon and infinite-horizon ruin probability asymptotics for risk processes with claims of subexponential tails for non-stationary arrival processes that satisfy a large deviation principle. As a result, the arrival process can be dependent, non-stationary and non-renewal. We give t…

Develops a deep non-stationary kernel for non-stationary spatio-temporal point processes.

Paper tackles non-stationary kernelized bandits with near-optimal algorithm.

The paper provides exact multivariate amplitude distributions for non-stationary Gaussian or algebraic fluctuations.

Efficient GP framework for scalable non-stationary processes.

Flexible GP model improves wind power prediction accuracy.

Develops large-sample theory for non-stationary source separation.

A new fuzzy time series method for non-stationary data.