Generalized polynomial approximations in Markovian decision processes
From MaRDI portal
Publication:1066821
DOI10.1016/0022-247X(85)90317-8zbMath0578.90091MaRDI QIDQ1066821
Abraham Seidmann, Paul J. Schweitzer
Publication date: 1985
Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)
Numerical mathematical programming methods (65K05) Linear programming (90C05) Markov and semi-Markov decision processes (90C40)
Related Items
A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications, Practical solution techniques for first-order MDPs, Approximate dynamic programming for stochastic linear control problems on compact state spaces, A methodology for computation reduction for specially structured large scale Markov decision problems, Approximate dynamic programming with state aggregation applied to UAV perimeter patrol, A unified DC programming framework and efficient DCA based approaches for large scale batch reinforcement learning, A Polyhedral Approach to Online Bipartite Matching, Approximate linear programming for networks: average cost bounds, Feature-based methods for large scale dynamic programming, Unnamed Item, Symmetric approximate linear programming for factored MDPs with application to constrained problems, Optimal recovery strategies for manufacturing systems, A strong Lagrangian relaxation for general discrete-choice network revenue management, State partitioning based linear program for stochastic dynamic programs: an invariance property, Reductions of non-separable approximate linear programs for network revenue management, Efficient compact linear programs for network revenue management, MF-OMO: An Optimization Formulation of Mean-Field Games, Computational bounds for elevator control policies by large scale linear programming, Hybrid least-squares algorithms for approximate policy evaluation, Using mathematical programming to solve factored Markov decision processes with imprecise probabilities, Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty, Optimal toll design: a lower bound framework for the asymmetric traveling salesman problem, Relationship between least squares Monte Carlo and approximate linear programming, Network-Based Approximate Linear Programming for Discrete Optimization, Identifying proactive ICU patient admission, transfer and diversion policies in a public-private hospital network, Relaxation Analysis for the Dynamic Knapsack Problem with Stochastic Item Sizes, A column and constraint generation algorithm for the dynamic knapsack problem with stochastic item sizes, Dynamic multi-appointment patient scheduling for radiation therapy, Value function approximation via linear programming for FMS scheduling, The actor-critic algorithm as multi-time-scale stochastic approximation., Reductions of Approximate Linear Programs for Network Revenue Management, Linear Programming and the Control of Diffusion Processes, Technical Note—A Note on Relaxations of the Choice Network Revenue Management Dynamic Program, A polyhedral approach to online bipartite matching, Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path, Computing Near-Optimal Policies in Generalized Joint Replenishment, Semi-Infinite Relaxations for the Dynamic Knapsack Problem with Stochastic Item Sizes, Data-driven optimal control with a relaxed linear program, Performance bounds and suboptimal policies for linear stochastic control via LMIs, Approximate dynamic programming via iterated Bellman inequalities, Unnamed Item
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Splines and efficiency in dynamic programming
- Dynamic programming, Markov chains, and the method of successive approximations
- A modified dynamic programming method for Markovian decision problems
- Linear programming algorithms for semi-Markovian decision processes
- Iterative solution of the functional equations of undiscounted Markov renewal programming
- Finite state Markovian decision processes
- Linear Programming and Markov Decision Chains
- Bounds and Transformations for Discounted Finite Markov Decision Chains
- The Functional Equations of Undiscounted Markov Renewal Programming
- Markov-Renewal Programming. I: Formulation, Finite Return Models
- Multichain Markov Renewal Programs
- Technical Note—Bounds on the Gain of a Markov Decision Process
- Multiple Policy Improvements in Undiscounted Markov Renewal Programming
- Polynomial Approximation--A New Computational Technique in Dynamic Programming: Allocation Processes
