TY - GEN
T1 - A Monte Carlo knowledge gradient method for learning abatement potential of emissions reduction technologies
AU - Ryzhov, Ilya O.
AU - Powell, Warren Buckler
N1 - Copyright:
Copyright 2010 Elsevier B.V., All rights reserved.
PY - 2009
Y1 - 2009
N2 - Suppose that we have a set of emissions reduction technologies whose greenhouse gas abatement potential is unknown, and we wish to find an optimal portfolio (subset) of these technologies. Due to the interaction between technologies, the effectiveness of a portfolio can only be observed through expensive field implementations. We view this problem as an online optimal learning problem with correlated prior beliefs, where the performance of a portfolio of technologies in one project is used to guide choices for future projects. Given the large number of potential portfolios, we propose a learning policy which uses Monte Carlo sampling to narrow down the choice set to a relatively small number of promising portfolios, and then applies a one-period look-ahead approach using knowledge gradients to choose among this reduced set. We present experimental evidence that this policy is competitive against other online learning policies that consider the entire choice set.
AB - Suppose that we have a set of emissions reduction technologies whose greenhouse gas abatement potential is unknown, and we wish to find an optimal portfolio (subset) of these technologies. Due to the interaction between technologies, the effectiveness of a portfolio can only be observed through expensive field implementations. We view this problem as an online optimal learning problem with correlated prior beliefs, where the performance of a portfolio of technologies in one project is used to guide choices for future projects. Given the large number of potential portfolios, we propose a learning policy which uses Monte Carlo sampling to narrow down the choice set to a relatively small number of promising portfolios, and then applies a one-period look-ahead approach using knowledge gradients to choose among this reduced set. We present experimental evidence that this policy is competitive against other online learning policies that consider the entire choice set.
UR - http://www.scopus.com/inward/record.url?scp=77951568757&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77951568757&partnerID=8YFLogxK
U2 - 10.1109/WSC.2009.5429301
DO - 10.1109/WSC.2009.5429301
M3 - Conference contribution
AN - SCOPUS:77951568757
SN - 9781424457700
T3 - Proceedings - Winter Simulation Conference
SP - 1492
EP - 1502
BT - Proceedings of the 2009 Winter Simulation Conference, WSC 2009
T2 - 2009 Winter Simulation Conference, WSC 2009
Y2 - 13 December 2009 through 16 December 2009
ER -