On the relative value iteration with a risk-sensitive criterion

DOI10.4064/bc122-1zbMath1460.90198arXiv1912.08758OpenAlexW3129918376MaRDI QIDQ4989140

Vivek S. Borkar, Aristotle Arapostathis

Publication date: 20 May 2021

Published in: Banach Center Publications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.08758

Mathematics Subject Classification ID

Continuous-time Markov processes on general state spaces (60J25) Sensitivity, stability, well-posedness (49K40) Optimal stochastic control (93E20) Diffusion processes (60J60) Markov and semi-Markov decision processes (90C40)

Related Items (1)

On the global convergence of relative value iteration for infinite-horizon risk-sensitive control of diffusions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Risk-sensitive control and an abstract Collatz-Wielandt formula
• Criteria for recurrence and existence of invariant measures for multidimensional diffusions
• Strict monotonicity of principal eigenvalues of elliptic operators in \(\mathbb R^d\) and risk-sensitive control
• Infinite horizon risk-sensitive control of diffusions without any blanket stability assumptions
• A topology for Markov controls
• The generalized principal eigenvalue for Hamilton-Jacobi-Bellman equations of ergodic type
• Average optimality for risk-sensitive control with general state space
• On the structure of solutions of ergodic type Bellman equation related to risk-sensitive control
• Selection theorems and their applications
• Relative Value Iteration for Stochastic Differential Games
• Ergodic Control of Diffusion Processes
• Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
• A Relative Value Iteration Algorithm for Nondegenerate Controlled Diffusions
• Ergodic Problems for Viscous Hamilton--Jacobi Equations with Inward Drift
• Large Time Behavior of Solutions of Hamilton--Jacobi--Bellman Equations with Quadratic Nonlinearity in Gradients
• Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
• Open Problem—Convergence and Asymptotic Optimality of the Relative Value Iteration in Ergodic Control
• A Correction to “A Relative Value Iteration Algorithm for Nondegenerate Controlled Diffusions
• Nonstationary value iteration in controlled Markov chains with risk-sensitive average criterion
• Convergence of the Relative Value Iteration for the Ergodic Control Problem of Nondegenerate Diffusions under Near-Monotone Costs
• Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost
• The Value Iteration Algorithm in Risk-Sensitive Average Markov Decision Chains with Finite State Space
• A Variational Formula for Risk-Sensitive Reward
• A Variational Characterization of the Risk-Sensitive Average Reward for Controlled Diffusions on $\mathbb{R}^d$

This page was built for publication: On the relative value iteration with a risk-sensitive criterion