Least squares policy iteration with instrumental variables vs. direct policy search: comparison against optimal benchmarks using energy storage

DOI10.1080/03155986.2019.1624491OpenAlexW2963530719WikidataQ114100489 ScholiaQ114100489MaRDI QIDQ5882386

Somayeh Moazeni, Warren B. Powell, Warren R. Scott

Publication date: 15 March 2023

Published in: INFOR: Information Systems and Operational Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1401.0843

zbMATH Keywords

dynamic programmingdirect policy searchapproximate dynamic programmingenergy storageapproximate policy iterationBellman error minimization

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Related Items (1)

Approximate dynamic programming for the dispatch of military medical evacuation assets

Uses Software

• S-PLUS

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Smoothing and parametric rules for stochastic mean-CVaR optimal execution strategy
• Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
• Instrumental variable methods for system identification
• Asynchronous stochastic approximation and Q-learning
• On the existence of fixed points for approximate value iteration and temporal-difference learning
• On the complexity of energy storage problems
• Optimal price-threshold control for battery operation with aging phenomenon: a quasiconvex optimization approach
• Basis function adaptation in temporal difference reinforcement learning
• A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications
• Dynamic-Programming Approximations for Stochastic Time-Staged Integer Multicommodity-Flow Problems
• Approximate Dynamic Programming
• Recursive Estimation and Time-Series Analysis
• An Approximate Dynamic Programming Approach to Benchmark Practice-Based Heuristics for Natural Gas Storage Valuation
• The Correlated Knowledge Gradient for Simulation Optimization of Continuous Parameters using Gaussian Process Regression
• Pricing in Electricity Markets: A Mean Reverting Jump Diffusion Model with Seasonality
• Algorithms for Reinforcement Learning
• The Linear Programming Approach to Approximate Dynamic Programming
• An analysis of temporal-difference learning with function approximation
• 10.1162/1532443041827907
• Least Squares Temporal Difference Methods: An Analysis under General Conditions
• Approximate dynamic programming via iterated Bellman inequalities
• An Optimal Approximate Dynamic Programming Algorithm for Concave, Scalar Storage Problems With Vector-Valued Controls
• Parallel Nonstationary Direct Policy Search for Risk-Averse Stochastic Optimization
• On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming
• Errors in Variables

This page was built for publication: Least squares policy iteration with instrumental variables vs. direct policy search: comparison against optimal benchmarks using energy storage