Constrained discounted Markov decision processes with Borel state spaces

DOI10.1016/j.automatica.2019.108582zbMath1434.90212arXiv1806.00190OpenAlexW2978834951MaRDI QIDQ2288591

Andrzej S. Nowak, Anna Jaśkiewicz, Eugene A. Feinberg

Publication date: 20 January 2020

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.00190

zbMATH Keywords

stochastic dynamic programmingstationary optimal policydeterministic optimal policyMarkov decision process with constraints

Mathematics Subject Classification ID

Stochastic programming (90C15) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Related Items (8)

Constrained discounted stochastic games ⋮ Unbounded dynamic programming via the Q-transform ⋮ Necessity of the terminal condition in the infinite horizon dynamic optimization problems with unbounded payoff ⋮ On approximate and weak correlated equilibria in constrained discounted stochastic games ⋮ A note on the existence of optimal stationary policies for average Markov decision processes with countable states ⋮ Extreme Occupation Measures in Markov Decision Processes with an Absorbing State ⋮ Fatou's Lemma for Weakly Converging Measures under the Uniform Integrability Condition ⋮ Constrained Markov Decision Processes with Expected Total Reward Criteria

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Conditions for the solvability of the linear programming formulation for constrained discounted Markov decision processes
• Convex analytic approach to constrained discounted Markov decision processes with non-constant discount factors
• Discounted dynamic programming with unbounded returns: application to economic models
• On dynamic programming and statistical decision theory
• A convex analytic approach to Markov decision processes
• On compactness of the space of policies in stochastic dynamic programming
• Stochastic optimal control. The discrete time case
• On dynamic programming: Compactness of the space of policies
• Markov programming by successive approximations with respect to weighted supremum norms
• Constrained Markov decision processes with total cost criteria: Lagrangian approach and dual linear program
• Constrained Markov control processes in Borel spaces: the discounted case
• Multiple objective nonatomic Markov decision processes with total reward criteria
• Constrained Markovian decision processes: The dynamic programming approach
• Finite approximations in discrete-time stochastic control. Quantized models and asymptotic optimality
• Nonatomic total rewards Markov decision processes with multiple criteria
• On the expected total reward with unbounded returns for Markov decision processes
• Non-randomized policies for constrained Markov decision processes
• Unbounded mappings and weak convergence of measures
• Measurable selections of extrema
• Splitting Randomized Stationary Policies in Total-Reward Markov Decision Processes
• Optimal flow control of a class of queueing networks in equilibrium
• Constrained Discounted Markov Decision Chains
• Constrained admission control to a queueing system
• Scorza Dragoni type theorems
• Ergodic Control of Markov Chains with Constraints—the General Case
• Constrained Discounted Dynamic Programming
• Constrained dynamic programming with two discount factors: applications and an algorithm
• Strategic measures in optimal control problems for stochastic sequences
• Sufficiency of Deterministic Policies for Atomless Discounted and Uniformly Absorbing MDPs with Multiple Criteria
• On Optimal Strategies in Control Problems with Constraints
• Constrained Markov Decision Models with Weighted Discounted Rewards
• Fatou's Lemma for Weakly Converging Measures under the Uniform Integrability Condition
• Dynamic Programming Equations for Discounted Constrained Stochastic Control

This page was built for publication: Constrained discounted Markov decision processes with Borel state spaces