An Approximate Dynamic Programming Algorithm for Monotone Value Functions
From MaRDI portal
Publication:2797467
DOI10.1287/opre.2015.1425zbMath1334.90194arXiv1401.1590OpenAlexW1915939971MaRDI QIDQ2797467
Warren B. Powell, Daniel R. Jiang
Publication date: 5 April 2016
Published in: Operations Research (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1401.1590
Related Items (12)
A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces ⋮ Optimal Liquidation in a Level-I Limit Order Book for Large-Tick Stocks ⋮ Poisoning finite-horizon Markov decision processes at design time ⋮ A numerical study of Markov decision process algorithms for multi-component replacement problems ⋮ Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications ⋮ Energy management for stationary electric energy storage systems: a systematic literature review ⋮ Meso-parametric value function approximation for dynamic customer acceptances in delivery routing ⋮ Linear programming formulation for non-stationary, finite-horizon Markov decision process models ⋮ Shape constraints in economics and operations research ⋮ Risk-Averse Approximate Dynamic Programming with Quantile-Based Risk Measures ⋮ Solving high-dimensional optimal stopping problems using deep learning ⋮ Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
Cites Work
- A simple nonparametric estimator of a strictly monotone regression function
- Optimizing the simultaneous management of blood pressure and cholesterol for type 2 diabetes patients
- Monotone optimal replacement policies for a Markovian deteriorating system in a controllable environment
- Monotone nonparametric regression
- Estimating a smooth monotone regression function
- Multi-stage stochastic optimization applied to energy planning
- Asynchronous stochastic approximation and Q-learning
- Kernel-based reinforcement learning
- \({\mathcal Q}\)-learning
- Exploiting structure in adaptive dynamic programming algorithms for a stochastic batch service problem
- An algorithm for approximating piecewise linear concave functions from sample gradients
- Properties of American option prices
- The Sample Average Approximation Method for Stochastic Discrete Optimization
- Approximate policy iteration: a survey and some new methods
- Optimal Energy Commitments with Storage and Intermittent Supply
- Optimal Replacement of GMC Bus Engines: An Empirical Model of Harold Zurcher
- Optimal Commodity Trading with a Capacitated Storage Asset
- Dynamic Programming Models and Algorithms for the Mutual Fund Cash Balance Problem
- An Optimal Approximate Dynamic Programming Algorithm for the Lagged Asset Acquisition Problem
- An Empirical Distribution Function for Sampling with Incomplete Information
- Maximum Likelihood Estimates of Monotone Parameters
- Optimal Hour-Ahead Bidding in the Real-Time Electricity Market with Battery Storage Using Approximate Dynamic Programming
- Valuation of energy storage: an optimal switching approach
- Structural Properties of Stochastic Dynamic Programs
- Decomposition and Partitioning Methods for Multistage Stochastic Linear Programs
- A survey of maintenance models: The control and surveillance of deteriorating systems
- Estimating Smooth Monotone Functions
- How Does the Value Function of a Markov Decision Process Depend on the Transition Probabilities?
- An adaptive dynamic programming algorithm for a stochastic multiproduct batch dispatch problem
- Regularized Decomposition of High-Dimensional Multistage Stochastic Programs with Markov Uncertainty
- Towards an Economic Theory of Replacement Investment
- Learning Algorithms for Separable Approximations of Discrete Stochastic Optimization Problems
This page was built for publication: An Approximate Dynamic Programming Algorithm for Monotone Value Functions