A Variational Formula for Risk-Sensitive Reward

DOI10.1137/151002630zbMath1361.93065arXiv1501.00676OpenAlexW2963056098MaRDI QIDQ5737636

Venkat Anantharam, Vivek S. Borkar

Publication date: 24 May 2017

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

Full work available at URL: https://arxiv.org/abs/1501.00676

zbMATH Keywords

risk-sensitive controlpositive operatorsPerron-Frobenius eigenvaluevariational formula

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Eigenvalue problems (93B60) Optimal stochastic control (93E20) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic systems in control theory (general) (93E03)

Related Items (14)

A convergent hierarchy of non-linear eigenproblems to compute the joint spectral radius of nonnegative matrices ⋮ A Convex Programming Approach to Solve Posynomial Systems ⋮ Risk-sensitive continuous-time Markov decision processes with unbounded rates and Borel spaces ⋮ Duality between large deviation control and risk-sensitive control for Markov decision processes ⋮ Risk-sensitivity vanishing limit for controlled Markov processes ⋮ Discrete-time zero-sum games for Markov chains with risk-sensitive average cost criterion ⋮ Spectral inequalities for nonnegative tensors and their tropical analogues ⋮ A game theory approach to the existence and uniqueness of nonlinear Perron-Frobenius eigenvectors ⋮ On the relative value iteration with a risk-sensitive criterion ⋮ A variational characterization of the optimal exit rate for controlled diffusions ⋮ The operator approach to entropy games ⋮ Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control ⋮ A Variational Characterization of the Risk-Sensitive Average Reward for Controlled Diffusions on $\mathbb{R}^d$ ⋮ “Controlled” Versions of the Collatz–Wielandt and Donsker–Varadhan Formulae

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Risk-sensitive control and an abstract Collatz-Wielandt formula
• On general minimax theorems
• Characterizations of the spectral radius of positive operators
• A note on negative dynamic programming for risk-sensitive control
• Nonlinear Perron-Frobenius problem for order-preserving mappings. I
• Risk sensitive control of Markov processes in countable state space
• Risk sensitive asset allocation
• Risk sensitive control of finite state Markov chains in discrete time, with applications to portfolio management
• A note on risk-sensitive control of invariant models
• Average optimality for risk-sensitive control with general state space
• A User's Guide to Measure Theoretic Probability
• Nonlinear Perron–Frobenius Theory
• Rényi Divergence and Kullback-Leibler Divergence
• Algorithms for sliding block codes - An application of symbolic dynamics to information theory
• On a Variational Formula for the Principal Eigenvalue for Operators with Maximum Principle
• Risk-Sensitive Control of Finite State Machines on an Infinite Horizon II
• Universal Portfolios
• Risk-Sensitive Control of Finite State Machines on an Infinite Horizon I
• An Introduction to Symbolic Dynamics and Coding
• Infinite Horizon Risk Sensitive Control of Discrete Time Markov Processes under Minorization Property
• Elements of Information Theory
• Existence of Optimal Strategies Based on Specified Information, for a Class of Stochastic Decision Problems
• Fixed-point and Minimax Theorems in Locally Convex Topological Linear Spaces

This page was built for publication: A Variational Formula for Risk-Sensitive Reward