Lipschitz continuous policy functions for strongly concave optimization problems
From MaRDI portal
We prove that the policy function, obtained by optimizing a discounted infinite sum of stationary return functions, is Lipschitz continuous when the instantaneous function is strongly concave. Moreover, by using the notion of \(\alpha\)-concavity, we provide an estimate of the Lipschitz constant which turns out to be a decreasing function of the discount factor.
Recommendations
- Lipschitz continuous dynamic programming with discount
- Lipschitz continuous dynamic programming with discount II
- Stochastic Lipschitz dynamic programming
- Policy gradient in Lipschitz Markov decision processes
- scientific article; zbMATH DE number 757681
- Lipschitz continuity of objective functions in stochastic programs with fixed recourse and its applications
- scientific article; zbMATH DE number 7403864
- On Lipschitz continuity of policy functions in continuous-time optimal growth models
- scientific article; zbMATH DE number 4062842
- Constrained, global optimization of unknown functions with Lipschitz continuous gradients
Cites work
- A local analysis of stability and regularity of stationary states in discrete symmetric optimal capital accumulation models
- Competitive chaos
- Discounted Dynamic Programming
- scientific article; zbMATH DE number 3504682 (Why is no real title available?)
- scientific article; zbMATH DE number 3505708 (Why is no real title available?)
- scientific article; zbMATH DE number 3595941 (Why is no real title available?)
- On the indeterminacy of capital accumulation paths
- Optimal decisions over time and strange attractors: an analysis by the Bellman principle
- Saddle points of Hamiltonian systems in convex Lagrange problems having a nonzero discount rate
- Smoothness, Comparative Dynamics, and the Turnpike Property
Cited in
(40)- Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
- Open-loop and closed-loop equilibria in dynamic games with many players
- A note on Shiu-Fisher-Weil immunization theorem
- On Lipschitz continuity of policy functions in continuous-time optimal growth models
- On the role of computation in economic theory
- Strong concavity properties of indirect utility functions in multisector optimal growth models
- A note on Shiu's immunization results
- Functions generating \((m,M,\Psi)\)-Schur-convex sums
- Jensen's and Hermite-Hadamard's type inequalities for lower and strongly convex functions on normed spaces
- On the sensitivity of optimal growth paths
- Remarks on \((F, t)\)-convex functions
- Lipschitz continuous dynamic programming with discount II
- Markovian equilibrium in infinite horizon economies with incomplete markets and public policy
- Lipschitz recursive equilibrium with a minimal state space and heterogeneous agents
- Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty
- Hölder continuity of the policy function approximation in the value function approximation
- A qualitative approach to Markovian equilibrium in infinite horizon economies with capital
- Stationary equilibria in discounted stochastic games with weakly interacting players
- Lipschitz continuous dynamic programming with discount
- Rational expectations equilibria of economies with local interactions
- Increasing Lipschitz continuous maximizers of some dynamic programs
- Competitive equilibrium cycles for small discounting in discrete-time two-sector optimal growth models
- On some properties of strictly convex functions
- Calmness and Stability Properties of Marginal and Performance Functions
- Optimality conditions and duality for multiobjective measurable subset selection problems
- Characterizations and decomposition of strongly Wright-convex functions of higher order
- Value and Policy Function Approximations in Infinite-Horizon Optimization Problems
- Stability of linear stochastic difference equations in strategically controlled random environments
- Cantor Type Invariant Distributions in the Theory of Optimal Growth under Uncertainty
- On strongly convex functions and related classes of functions
- Smooth dynamics and computation in models of economic growth
- Smooth dynamics and computation in models of economic growth
- Block-recursive equilibria in heterogeneous-agent models
- Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
- Discounted dynamic optimization and Bregman divergence
- Near optimality of Lipschitz and smooth policies in controlled diffusions
- A turnpike theorem for continuous-time optimal-control models
- Policy gradient in Lipschitz Markov decision processes
- Lipschitz continuity of value functions in Markovian decision processes
- On Lipschitz continuity of the iterated function system in a stochastic optimal growth model
This page was built for publication: Lipschitz continuous policy functions for strongly concave optimization problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1098779)
