Abstract: We consider dynamic programming problems with a large time horizon, and give sufficient conditions for the existence of the uniform value. As a consequence, we obtain an existence result when the state space is precompact, payoffs are uniformly continuous and the transition correspondence is non expansive. In the same spirit, we give an existence result for the limit value. We also apply our results to Markov decision processes and obtain a few generalizations of existing results.
Recommendations
- General limit value in dynamic programming
- Asymptotic properties in dynamic programming
- Low discounting and the upper long-run average value in dynamic programming
- Strong uniform value in gambling houses and partially observable Markov decision processes
- A Uniform Tauberian Theorem in Dynamic Programming
Cited in
(32)- Bounded variation of \(\{V_ n\}\) and its limit
- Tauberian theorem for value functions
- An accretive operator approach to ergodic zero-sum stochastic games
- A game theory approach to the existence and uniqueness of nonlinear Perron-Frobenius eigenvectors
- Communicating zero-sum product stochastic games
- Linear programming formulations of deterministic infinite horizon optimal control problems in discrete time
- Generic uniqueness of the bias vector of finite zero-sum stochastic games with perfect information
- Asymptotic properties of optimal trajectories in dynamic programming
- Ergodicity conditions for zero-sum games
- On values of repeated games with signals
- A survey of average cost problems in deterministic discrete-time control systems
- Finitely additive dynamic programming
- Strong uniform value in gambling houses and partially observable Markov decision processes
- A Tauberian theorem for nonexpansive operators and applications to zero-sum stochastic games
- Acyclic Gambling Games
- A zero-sum stochastic game with compact action sets and no asymptotic value
- Existence of the uniform value in zero-sum repeated games with a more informed controller
- General limit value in dynamic programming
- On representation formulas for long run averaging optimal control problem
- History-dependent evaluations in partially observable Markov decision process
- Finite-memory strategies in POMDPs with long-run average objectives
- Representation formulas for limit values of long run stochastic optimal controls
- Stochastic games
- Definable zero-sum stochastic games
- Commutative Stochastic Games
- Vanishing Discount Limit and Nonexpansive Optimal Control and Differential Games
- Asymptotic control for a class of piecewise deterministic Markov processes associated to temperate viruses
- Long-term values in Markov decision processes and repeated games, and a new distance for probability spaces
- Analysis of the vanishing discount limit for optimal control problems in continuous and discrete time
- Existence of asymptotic values for nonexpansive stochastic control systems
- LP based upper and lower bounds for Cesàro and Abel limits of the optimal values in problems of control of stochastic discrete time systems
- Limit value for optimal control with general means
This page was built for publication: Uniform value in dynamic programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q621850)
