Least squares policy iteration with instrumental variables vs. direct policy search : comparison against optimal benchmarks using energy storage
Year of publication: |
2020
|
---|---|
Authors: | Moazeni, Somayeh ; Scott, Warren R. ; Powell, Warren B. |
Published in: |
INFOR : information systems and operational research. - Abingdon : Taylor & Francis Group, ISSN 1916-0615, ZDB-ID 1468358-1. - Vol. 58.2020, 1, p. 141-166
|
Subject: | Dynamic programming | approximate dynamic programming | approximate policy iteration | Bellman error minimization | direct policy search | energy storage | Energiepolitik | Energy policy | Mathematische Optimierung | Mathematical programming | Dynamische Optimierung | USA | United States | Theorie | Theory | Algorithmus | Algorithm |
-
Parallel nonstationary direct policy search for risk-averse stochastic optimization
Moazeni, Somayeh, (2017)
-
On the taylor expansion of value functions
Braverman, Anton, (2020)
-
Online allocation and pricing : constant regret via Bellman inequalities
Vera, Alberto, (2021)
- More ...
-
Moazeni, Somayeh, (2018)
-
Parallel nonstationary direct policy search for risk-averse stochastic optimization
Moazeni, Somayeh, (2017)
-
Smoothed Histograms for Frequency Data on Irregular Intervals
Scott, David W., (2008)
- More ...