Discrete-time zero-sum games for Markov chains with risk-sensitive average cost criterion

DOI10.1016/j.spa.2022.12.009OpenAlexW4312220394MaRDI QIDQ2689890

Chandan Pal, Somnath Pradhan, Subrata Golui, Mrinal K. Ghosh

Publication date: 14 March 2023

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.03790

zbMATH Keywords

value functionsaddle point equilibriumrisk-sensitive average cost criterionShapley equationshistory dependent strategiesrisk-sensitive zero-sum game

Mathematics Subject Classification ID

Noncooperative games (91A10) Discrete-time games (91A50) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic games, stochastic differential games (91A15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A counterexample on sample-path optimality in stable Markov decision chains with the average reward criterion
• Markov chains and stochastic stability
• Zero-sum risk-sensitive stochastic games
• Continuous-time Markov decision processes. Theory and applications
• Stochastic optimal control. The discrete time case
• Equivalence of Lyapunov stability criteria in a class of Markov decision processes
• Nonlinear Perron-Frobenius problem for order-preserving mappings. I
• Strict monotonicity of principal eigenvalues of elliptic operators in \(\mathbb R^d\) and risk-sensitive control
• A counterexample to a nonlinear version of the Kreĭn-Rutman theorem by R.\,Mahadevan
• Infinite horizon risk-sensitive control of diffusions without any blanket stability assumptions
• Large deviations asymptotics and the spectral theory of multiplicatively regular Markov proces\-ses
• A characterization of the optimal risk-sensitive average cost in finite controlled Markov chains
• Adaptive Markov control processes
• Existence of risk-sensitive optimal stationary policies for controlled Markov processes
• Spectral theory and limit theorems for geometrically ergodic Markov processes
• Multiplicative ergodicity and large deviations for an irreducible Markov chain.
• Controlled Markov chains with risk-sensitive criteria: Average cost, optimality equations, and optimal solutions
• Nonzero-sum games for continuous-time jump processes under the expected average payoff criterion
• Nonzero-sum risk-sensitive average stochastic games: The case of unbounded costs
• Risk-sensitive continuous-time Markov decision processes with unbounded rates and Borel spaces
• A note on a nonlinear Krein-Rutman theorem
• An eigenvalue approach to the risk sensitive control problem in near monotone case
• Zero-sum risk-sensitive stochastic games on a countable state space
• Risk-sensitive control of pure jump process on countable space with near monotone cost
• Risk-sensitive control of continuous time Markov chains
• Zero-sum risk-sensitive stochastic games for continuous time Markov chains
• Nonlinear Perron–Frobenius Theory
• Sample-Path Optimal Stationary Policies in Stable Markov Decision Chains with the Average Reward Criterion
• Risk-Sensitive Ergodic Control of Continuous Time Markov Processes With Denumerable State Space
• Risk-sensitive linear/quadratic/gaussian control
• Risk-Sensitive Control of Finite State Machines on an Infinite Horizon I
• Zero-sum games for continuous-time Markov chains with unbounded transition and average payoff rates
• Risk-sensitive average continuous-time Markov decision processes with unbounded rates
• Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
• Risk-Sensitive Discounted Continuous-Time Markov Decision Processes with Unbounded Rates
• On the policy improvement algorithm for ergodic risk-sensitive control
• Risk sensitive control of pure jump processes on a general state space
• More Risk-Sensitive Markov Decision Processes
• Average optimality for continuous-time Markov decision processes under weak continuity conditions
• Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games
• Nonzero-Sum Risk-Sensitive Stochastic Games on a Countable State Space
• Fatou's Lemma for Weakly Converging Probabilities
• Infinite Horizon Risk Sensitive Control of Discrete Time Markov Processes under Minorization Property
• Risk-Sensitive Markov Decision Processes
• Nonzero-sum games for continuous-time Markov chains with unbounded discounted payoffs
• Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost
• A Variational Formula for Risk-Sensitive Reward
• Minimax Theorems
• Ergodic risk-sensitive control of Markov processes on countable state space revisited

This page was built for publication: Discrete-time zero-sum games for Markov chains with risk-sensitive average cost criterion