This is a PhD thesis of Blagoj Delipetrev explaining nested dynamic programming, nested stochastic dynamic programming and nested reinforcement learning algorithms that are applied in reservoir optimization problem. Additionally there are also multi-objective version of these algorithms.
Cite
@article{arxiv.1611.02308,
title = {Nested algorithms for optimal reservoir operation and their embedding in a decision support platform},
author = {Blagoj Delipetrev},
journal= {arXiv preprint arXiv:1611.02308},
year = {2016}
}