On the relative value iteration with a risk-sensitive criterion
From MaRDI portal
(Redirected from Publication:4989140)
Abstract: A multiplicative relative value iteration algorithm for solving the dynamic programming equation for the risk-sensitive control problem is studied for discrete time controlled Markov chains with a compact Polish state space, and controlled diffusions in on the whole Euclidean space. The main result is a proof of convergence to the desired limit in each case.
Recommendations
- Value iteration methods in risk minimizing stopping problems
- Approximate Value Iteration for Risk-Aware Markov Decision Processes
- The Value Iteration Algorithm in Risk-Sensitive Average Markov Decision Chains with Finite State Space
- On the global convergence of relative value iteration for infinite-horizon risk-sensitive control of diffusions
- Risk-sensitive discounted cost criterion for continuous-time Markov decision processes on a general state space
- Relative Value Iteration for Stochastic Differential Games
- A variational formula for risk-sensitive reward
- Risk-sensitive semi-Markov decision processes with general utilities and multiple criteria
- Risk-sensitive estimation and a differential game
- Iterative estimation maximization for stochastic linear programs with conditional value-at-risk constraints
Cites work
- A correction to ``A relative value iteration algorithm for nondegenerate controlled diffusions
- A relative value iteration algorithm for nondegenerate controlled diffusions
- A topology for Markov controls
- A variational characterization of the risk-sensitive average reward for controlled diffusions on \(\mathbb{R}^d\)
- A variational formula for risk-sensitive reward
- Average optimality for risk-sensitive control with general state space
- Convergence of the relative value iteration for the ergodic control problem of nondegenerate diffusions under near-monotone costs
- Criteria for recurrence and existence of invariant measures for multidimensional diffusions
- Ergodic control of diffusion processes.
- Ergodic problems for viscous Hamilton-Jacobi equations with inward drift
- scientific article; zbMATH DE number 3152028 (Why is no real title available?)
- scientific article; zbMATH DE number 3538599 (Why is no real title available?)
- scientific article; zbMATH DE number 3277871 (Why is no real title available?)
- Infinite horizon risk-sensitive control of diffusions without any blanket stability assumptions
- Large time behavior of solutions of Hamilton-Jacobi-Bellman equations with quadratic nonlinearity in gradients
- Nonstationary value iteration in controlled Markov chains with risk-sensitive average criterion
- On the structure of solutions of ergodic type Bellman equation related to risk-sensitive control
- Open Problem—Convergence and Asymptotic Optimality of the Relative Value Iteration in Ergodic Control
- Relative Value Iteration for Stochastic Differential Games
- Risk-sensitive control and an abstract Collatz-Wielandt formula
- Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
- Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost
- Selection theorems and their applications
- Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
- Strict monotonicity of principal eigenvalues of elliptic operators in \(\mathbb R^d\) and risk-sensitive control
- The generalized principal eigenvalue for Hamilton-Jacobi-Bellman equations of ergodic type
- The Value Iteration Algorithm in Risk-Sensitive Average Markov Decision Chains with Finite State Space
Cited in
(5)- On the global convergence of relative value iteration for infinite-horizon risk-sensitive control of diffusions
- On the policy improvement algorithm for ergodic risk-sensitive control
- A correction to ``A relative value iteration algorithm for nondegenerate controlled diffusions
- Q-Learning for Risk-Sensitive Control
- A note on negative dynamic programming for risk-sensitive control
This page was built for publication: On the relative value iteration with a risk-sensitive criterion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4989140)
