Universal approximators for direct policy search in multi-purpose water reservoir management: A comparative analysis

详细信息    查看全文

• 作者：Matteo Giuliani^* ; ^{matteo.giuliani@polimi.it" class="auth_mail" title="E-mail the corresponding author} ; Emanuele Mason^* ; ^{emanuele.mason@polimi.it" class="auth_mail" title="E-mail the corresponding author} ; Andrea Castelletti^* ; ^{andrea.castelletti@polimi.it" class="auth_mail" title="E-mail the corresponding author} ; Francesca Pianosi^** ; ^{francesca.pianosi@bristol.ac.uk" class="auth_mail" title="E-mail the corresponding author} ; Rodolfo Soncini-Sessa^* ; ^{rodolfo.soncini@polimi.it" class="auth_mail" title="E-mail the corresponding author}
• 关键词：radial basis functions ; artificial neural networks ; direct policy search ; multi-objective optimization ; environmental engineering
• 刊名：IFAC-PapersOnLine
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：47
• 期：3
• 页码：6234-6239
• 全文大小：1052 K

文摘

This study presents a novel approach which combines direct policy search and multi-objective evolutionary algorithms to solve high-dimensional state and control space water resources problems involving multiple, conflicting, and non-commensurable objectives. In such a multi-objective context, the use of universal function approximators is generally suggested to provide flexibility to the shape of the control policy. In this paper, we comparatively analyze Artificial Neural Networks (ANN) and Radial Basis Functions (RBF) under different sets of input to estimate their scalability to high-dimensional state space problems. The multi-purpose HoaBinh water reservoir in Vietnam, accounting for hydropower production and flood control, is used as a case study. Results show that the RBF policy parametrization is more effective than the ANN one. In particular, the approximated Pareto front obtained with RBF control policies successfully explores the full tradeoff space between the two conflicting objectives, while the ANN solutions are often Pareto-dominated by the RBF ones.