On the reduction of total‐cost and average‐cost MDPs to discounted MDPs
From MaRDI portal
Publication:3120606
DOI10.1002/nav.21743zbMath1407.90089arXiv1507.00664OpenAlexW2962736516MaRDI QIDQ3120606
Jefferson Huang, Eugene A. Feinberg
Publication date: 5 March 2019
Published in: Naval Research Logistics (NRL) (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1507.00664
Linear programming (90C05) Stochastic network models in operations research (90B15) Markov and semi-Markov decision processes (90C40)
Related Items (5)
On the evaluation of bidding strategies in sequential auctions ⋮ Reduction of total-cost and average-cost MDPs with weakly continuous transition probabilities to discounted mdps ⋮ Solutions of the average cost optimality equation for Markov decision processes with weakly continuous kernel: the fixed-point approach revisited ⋮ Improved bound on the worst case complexity of policy iteration ⋮ Characterization of the Optimal Risk-Sensitive Average Cost in Denumerable Markov Decision Chains
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
- Unnamed Item
- Unnamed Item
- The multi-armed bandit, with constraints
- Matrix multiplication via arithmetic progressions
- On polynomial cases of the unichain classification problem for Markov decision processes
- Stochastic optimal control. The discrete time case
- The critical discount factor for finite Markovian decision processes with an absorbing set
- The value iteration algorithm is not strongly polynomial for discounted dynamic programming
- Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming
- A bound for the number of different basic solutions generated by the simplex method
- Strong polynomiality of the Gass-Saaty shadow-vertex pivoting rule for controlled random walks
- Strong polynomiality of policy iterations for average-cost MDPs modeling replacement and maintenance problems
- NP-hardness of checking the unichain condition in average cost MDPs
- Gaussian elimination is not optimal
- Measurable selections of extrema
- Recurrence conditions for Markov decision processes with Borel state space: A survey
- The Simplex and Policy-Iteration Methods Are Strongly Polynomial for the Markov Decision Problem with a Fixed Discount Rate
- Splitting Randomized Stationary Policies in Total-Reward Markov Decision Processes
- Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
- A Strongly Polynomial Algorithm for Controlled Queues
- Improved and Generalized Upper Bounds on the Complexity of Policy Iteration
- Transient policies in discrete dynamic programming: Linear programming including suboptimality tests and additional constraints
- Growth Optimality for Branching Markov Decision Chains
- Recurrence Conditions for Average and Blackwell Optimality in Denumerable State Markov Decision Chains
- Normalized Markov Decision Chains I; Sensitive Discount Optimality
- Optimization of Multitype Branching Processes
- The optimality equation in average cost denumerable state semi-Markov decision problems, recurrency conditions and algorithms
- On the Relation Between Recurrence and Ergodicity Properties in Denumerable Markov Decision Chains
- Average Optimality in Dynamic Programming with General State Space
- Maximum-Stopping-Value Policies in Finite Markov Population Decision Chains
- Algorithms for Countable State Markov Decision Models with an Absorbing Set
- Risk-Sensitive and Risk-Neutral Multiarmed Bandits
- Strategy Iteration Is Strongly Polynomial for 2-Player Turn-Based Stochastic Games with a Constant Discount Factor
- Contraction Mappings in the Theory Underlying Dynamic Programming
- Non-Discounted Denumerable Markovian Decision Models
- Arbitrary State Markovian Decision Processes
- Discrete Dynamic Programming with Sensitive Discount Optimality Criteria
This page was built for publication: On the reduction of total‐cost and average‐cost MDPs to discounted MDPs
