arXiv research

The paper optimizes policies constrained to Schur stabilizing controllers using a Newton-type algorithm.

We improve Riemannian metrics for constrained systems control.

Paper studies constrained control games with a novel approximation method.

Optimal control problems on Riemannian manifolds are solved by penalizing constraint violations.

We present a novel technique to solve the problem of managing optimally a pumped hydroelectric storage system. This technique relies on representing the system as a stochastic optimal control problem with state constraints, these latter corresponding to the finite volume of the reservoirs. Following the recent level-se…

Counterexample shows state-constrained optimal control problems can have Young measure gaps.

Controller-Augmented Hidden Markov Models (CHMMs) are a framework for constrained sequential inference.

Study uses DRL with Lagrangian relaxation to solve temporal control tasks with STL constraints.

New conditions prevent gaps in optimal control problems.

We study in this paper a class of constrained linear-quadratic (LQ) optimal control problem formulations for the scalar-state stochastic system with multiplicative noise, which has various applications, especially in the financial risk management. The linear constraint on both the control and state variables considered…

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

We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a framework which allows for system identification through persistent excitation, while maintaining safety by guaranteeing the satisfaction of st…

This paper studies a class of continuous-time scalar-state stochastic Linear-Quadratic (LQ) optimal control problem with the linear control constraints. Applying the state separation theorem induced from its special structure, we develop the explicit solution for this class of problem. The revealed optimal control poli…

Algorithm mitigates performance loss in constrained reinforcement learning with model misspecification.

We study a constrained optimal control problem with possibly degenerate coefficients arising in models of optimal portfolio liquidation under market impact. The coefficients can be random in which case the value function is described by a degenerate backward stochastic partial differential equation (BSPDE) with singula…

In this paper, we describe a constrained Lagrangian and Hamiltonian formalism for the optimal control of nonholonomic mechanical systems. In particular, we aim to minimize a cost functional, given initial and final conditions where the controlled dynamics is given by nonholonomic mechanical system. In our paper, the co…

Develops neural network framework for risk-reward optimization problems.

We investigate Monte Carlo based algorithms for solving stochastic control problems with probabilistic constraints. Our motivation comes from microgrid management, where the controller tries to optimally dispatch a diesel generator while maintaining low probability of blackouts. The key question we investigate are empi…

New method optimizes costly evaluations in Bayesian optimization.

New approach to control diffusion processes with soft constraints.

New algorithms boost SAT solver performance by optimizing restart strategies.

This paper studies a class of non$-$Markovian singular stochastic control problems, for which we provide a novel probabilistic representation. The solution of such control problem is proved to identify with the solution of a $Z-$constrained BSDE, with dynamics associated to a non singular underlying forward process. Du…

New method solves constrained optimization problems efficiently.

We investigate the capacity, convexity and characterization of a general family of norm-constrained feed-forward networks.

This work establishes safe reinforcement learning for LQR with nonlinear baselines.

SCBO tackles constrained optimization in high dimensions.

CCC clusters with controlled spread, outperforming standard methods.

Three physics-constrained regression exercises for image velocimetry and turbulence modeling.

We consider a singular control problem with regime switching that arises in problems of optimal investment decisions of cash-constrained firms. The value function is proved to be the unique viscosity solution of the associated Hamilton-Jacobi-Bellman equation. Moreover, we give regularity properties of the value functi…

We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to generate image trajectories from a latent space in which the dynamics is constr…

The control and sensing of large-scale systems results in combinatorial problems not only for sensor and actuator placement but also for scheduling or observability/controllability. Such combinatorial constraints in system design and implementation can be captured using a structure known as matroids. In particular, the…

A new pricing controller handles resource constraints to infer target prices effectively.

Paper solves MV portfolio selection in jump-diffusion models with no-shorting constraint.

In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical …

A new Bayesian optimization method tackles constrained optimization with uncertainties.

New method reduces variance in Bayesian inverse problems.

This work proposes an online learning approach to tighten constraints in stochastic control problems.

New method controls renewable energy storage and portfolio selection with probabilistic constraints.

In E-commerce advertising, where product recommendations and product ads are presented to users simultaneously, the traditional setting is to display ads at fixed positions. However, under such a setting, the advertising system loses the flexibility to control the number and positions of ads, resulting in sub-optimal p…

The paper proves index theorems for graph-based optimal control problems.

Unified market making controls risk, arbitrage, and volatility surfaces.

Neural ODEs control graph dynamics with low energy feedback.

Optimizes control interventions in real-world networks using deep-learning and network science.

We solve the problem of optimal stopping of a Brownian motion subject to the constraint that the stopping time's distribution is a given measure consisting of finitely-many atoms. In particular, we show that this problem can be converted to a finite sequence of state-constrained optimal control problems with additional…

New algorithms for constrained online optimization with memory and predictions.

Improved COCO algorithms with better constraint control.

PLoM learns stochastic solutions to PDEs with limited data.

We devise an optimal allocation strategy for the execution of a predefined number of stocks in a given time frame using the technique of discrete-time Stochastic Control Theory for a defined market model. This market structure allows an instant execution of the market orders and has been analyzed based on the assumptio…