Exploratory HJB Equations and Their Convergence

DOI10.1137/21M1448185zbMath1501.35132arXiv2109.10269OpenAlexW4309029392MaRDI QIDQ5047935

No author found.

Publication date: 17 November 2022

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2109.10269

zbMATH Keywords

stochastic controlsimulated annealingreinforcement learningoverdamped Langevin equationentropy regularizationexploratory controlHamilton-Jacobi-Bellmann (HJB) equations

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Stochastic stability in control theory (93E15) Diffusion processes (60J60) Hamilton-Jacobi equations (35F21)

Related Items (2)

Choquet Regularization for Continuous-Time Reinforcement Learning ⋮ Exploratory Control with Tsallis Entropy for Latent Factor Models

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Comparison principle for unbounded viscosity solutions of degenerate elliptic PDEs with gradient superlinear terms
• Viscosity solutions of fully nonlinear second-order elliptic partial differential equations
• \(W^{1,p}\)-interior estimates for solutions of fully nonlinear, uniformly elliptic equations
• The Poisson equation and estimates for distances between stationary distributions of diffusions
• Exploratory LQG mean field games with entropy regularization
• Exponential ergodicity and convergence for generalized reflected Brownian motion
• Viscosity solutions of general viscous Hamilton-Jacobi equations
• The Kantorovich and variation distances between invariant measures of diffusions and nonlinear stationary Fokker-Planck-Kolmogorov equations
• Controlled Markov processes and viscosity solutions
• Stability of Markovian processes II: continuous-time processes and sampled chains
• Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
• Regularity and Stability of Feedback Relaxed Controls
• Fokker–Planck–Kolmogorov Equations
• On the regularity theory of fully nonlinear parabolic equations: I
• On the regularity theory of fully nonlinear parabolic equations: II
• User’s guide to viscosity solutions of second order partial differential equations
• Nonuniqueness for Second-Order Elliptic Equations with Measurable Coefficients
• L^p- Theory for fully nonlinear uniformly parabolic equations
• Distances between Stationary Distributions of Diffusions and Solvability of Nonlinear Fokker--Planck--Kolmogorov Equations
• State-Dependent Temperature Control for Langevin Diffusions
• Bounds for the fundamental solution of a parabolic equation
• The Alexandrov-Bakelman-Pucci Weak Maximum Principle for Fully Nonlinear Equations in Unbounded Domains
• Continuous‐time mean–variance portfolio selection: A reinforcement learning framework
• Entropy Regularization for Mean Field Games with Learning

This page was built for publication: Exploratory HJB Equations and Their Convergence