Results 11 to 20 of about 638 (186)
Exploratory HJB Equations and Their Convergence
SIAM Journal on Control and Optimization, 2022 We study the exploratory Hamilton--Jacobi--Bellman (HJB) equation arising from the entropy-regularized exploratory control problem, which was formulated by Wang, Zariphopoulou and Zhou (J. Mach. Learn. Res., 21, 2020) in the context of reinforcement learning in continuous time and space.
Wenpin Tang +2 more
openaire +3 more sources
PINN-based viscosity solution of HJB equation
CoRR, 2023 This paper proposed a novel PINN-based viscosity solution for HJB equations. Although there exists work using PINN to solve HJB, but none of them gives the solution in viscosity sense. This paper reveals the fact that using the convex neural network, one can guarantee the viscosity solution and thus the neural network can easily converge to the true ...
Tianyu Liu 0003 +3 more
openaire +2 more sources
Series Solution of Stochastic HJB Equations [PDF]
2019 IEEE 58th Conference on Decision and Control (CDC), 2019 We consider infinite horizon, stochastic, smooth optimal control problems in continuous time where the coefficients of the white Gaussian noise terms in the dynamics vanish at the origin. We show how the Taylor polynomials of the optimal cost and the optimal feedback can be computed degree by degree. This is a generaliztion of the work of Al’brekht who
openaire +4 more sources
Observer-Based Adaptive Control of Uncertain Nonlinear Systems Via Neural Networks
IEEE Access, 2018 In this paper, a novel observer-based control strategy is proposed for a class of uncertain continuous-time nonlinear systems based on the Hamilton-Jacobi-Bellman (HJB) equation.
Chaoxu Mu, Yong Zhang, Ke Wang
doaj +1 more source
SICE Journal of Control, Measurement, and System Integration, 2020 This paper presents a numerical approach to solve the Hamilton-Jacobi-Bellman (HJB) equation, which arises in nonlinear optimal control. In this approach, we first use the successive approximation to reduce the HJB equation, a nonlinear partial ...
Ichiro Maruta +2 more
doaj +1 more source
IEEE Access, 2021 In this article, an optimized tracking control using critic-actor reinforcement learning (RL) strategy is investigated for a class of non-affine nonlinear continuous-time systems.
Xue Yang, Bin Li, Guoxing Wen
doaj +1 more source
Optimal Consumption in a Stochastic Ramsey Model with Cobb-Douglas Production Function
International Journal of Mathematics and Mathematical Sciences, 2013 A stochastic Ramsey model is studied with the Cobb-Douglas production function maximizing the expected discounted utility of consumption. We transformed the Hamilton-Jacobi-Bellman (HJB) equation associated with the stochastic Ramsey model so as to ...
Md. Azizul Baten, Anton Abdulbasah Kamil
doaj +1 more source
Optimal Surplus-Dependent Reinsurance under Regime-Switching in a Brownian Risk Model
Risks, 2021 In this paper, we consider a company that wishes to determine the optimal reinsurance strategy minimising the total expected discounted amount of capital injections needed to prevent the ruin. The company’s surplus process is assumed to follow a Brownian
Julia Eisenberg +2 more
doaj +1 more source
Triangle Inequality for Inverse Optimal Control
IEEE Access, 2023 Inverse optimal control (IOC) is a problem of estimating a cost function based on the behaviors of an expert that behaves optimally with respect to the cost function.
Sho Mitsuhashi, Shin Ishii
doaj +1 more source
Optimal feedback control for undamped wave equations by solving a HJB equation [PDF]
ESAIM: Control, Optimisation and Calculus of Variations, 2015 In this paper, optimal feedback control for one-dimensional semi-linear wave equations is considered. The feedback law based on the dynamic programming principle requires to solve the evolutionary Hamilton-Jacobi-Bellman (HJB) equation. To avoid the so--called ``curse of dimensionality'', instead of classical discretization methods based on finite ...
Kröner, Axel +2 more
openaire +3 more sources