Unbounded dynamic programming via the Q-transform
From MaRDI portal
Publication:2138381
Abstract: We propose a new approach to solving dynamic decision problems with unbounded rewards based on the transformations used in Q-learning. In our case, the objective of the transform is to convert an unbounded dynamic program into a bounded one. The approach is general enough to handle problems for which existing methods struggle, and yet simple relative to other techniques and accessible for applied work. We show by example that many common decision problems satisfy our conditions.
Recommendations
- Discounted dynamic programming with unbounded returns: application to economic models
- scientific article; zbMATH DE number 1536370
- Ordered Solutions for Dynamic Programs
- A simulation-based approach to stochastic dynamic programming
- Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards
Cites work
- scientific article; zbMATH DE number 3692995 (Why is no real title available?)
- scientific article; zbMATH DE number 52448 (Why is no real title available?)
- scientific article; zbMATH DE number 1325008 (Why is no real title available?)
- scientific article; zbMATH DE number 6931762 (Why is no real title available?)
- A theory of the saving rate of the rich
- An impossibility theorem for wealth in heterogeneous-agent models with limited heterogeneity
- Average cost Markov decision processes with weakly continuous transition probabilities
- Berge's theorem for noncompact image sets
- Constrained discounted Markov decision processes with Borel state spaces
- Consumption and Portfolio Policies With Incomplete Markets and Short‐Sale Constraints: the Finite‐Dimensional Case1
- Correlation inequalities on some partially ordered sets
- Discounted Dynamic Programming
- Discounted dynamic programming with unbounded returns: application to economic models
- Discrete Dynamic Programming
- Dynamic programming and optimal control. Vol. 1.
- Dynamic programming deconstructed: transformations of the Bellman equation and computational efficiency
- Dynamic programming with homogeneous functions
- Elementary results on solutions to the Bellman equation of dynamic programming: existence, uniqueness, and convergence
- Existence and Uniqueness of Solutions to the Bellman Equation in the Unbounded Case
- Existence and uniqueness of a fixed point for local contractions
- Existence of stationary equilibrium in an incomplete-market model with endogenous labor supply
- Heterogeneity and persistence in returns to wealth
- Incomplete market dynamics and cross-sectional distributions
- Infinite dimensional analysis. A hitchhiker's guide.
- MDPs with setwise continuous transition probabilities
- Markov decision processes with applications to finance.
- Markov programming by successive approximations with respect to weighted supremum norms
- On discounted dynamic programming with unbounded returns
- Optimal Replacement of GMC Bus Engines: An Empirical Model of Harold Zurcher
- Optimal timing of decisions: a general theory based on continuation values
- Recursive equilibria in an Aiyagari-style economy with permanent income shocks
- Recursive equilibrium in Krusell and Smith (1998)
- Recursive utility and optimal growth with bounded or unbounded returns
- Recursive utility and the Ramsey problem
- Robustness
- Selection and the Evolution of Industry
- Stochastic finance. An introduction in discrete time
- Stochastic optimal growth model with risk sensitive preferences
- Take the short route: equilibrium default and debt maturity
- The income fluctuation problem and the evolution of wealth
- The persistent-transitory representation for earnings processes
- The wealth distribution in Bewley economies with capital income risk
- Very simple Markov-perfect industry dynamics: theory
- \({\mathcal Q}\)-learning
Cited in
(5)- Existence and uniqueness of solutions to the Bellman equation in stochastic dynamic programming
- Do not blame Bellman: it is Koopmans' fault
- Dynamic programming deconstructed: transformations of the Bellman equation and computational efficiency
- An approximation approach to dynamic programming with unbounded returns
- Fifty years of mathematical growth theory: classical topics and new trends
This page was built for publication: Unbounded dynamic programming via the Q-transform
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2138381)
