A novel nested stochastic dynamic programming (nSDP) and nested reinforcement learning (nRL) algorithm for multipurpose reservoir optimization

نویسندگان
چکیده

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Benders, Nested Benders and Stochastic Programming

This article aims to explain the Nested Benders algorithm for the solution of large-scale stochastic programming problems in a way that is intelligible to someone coming to it for the first time. In doing so it gives an explanation of Benders decomposition and of its application to two-stage stochastic programming problems (also known in this context as the L-shaped method), then extends this t...

متن کامل

Multiobjective Reinforcement Learning Using Adaptive Dynamic Programming And Reservoir Computing

This paper introduces a multiobjective reinforcement learning approach which is suitable for large state and action spaces. The approach is based on actorcritic design and reservoir computing. A single reservoir estimates several utilities simultaneously and provides their gradients that are required for the actor enabling an agent to adapt its behavior in presence of several sources of rewards...

متن کامل

Nested algorithms for optimal reservoir operation and their embedding in a decision support platform

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.

متن کامل

B-Learning: A Reinforcement Learning Algorithm, Comparison with Dynamic Programming

In this paper we present a Reinforcement Learning method | B-Learning | for the control of a water production plant. A comparison between B-Learning and Dynamic Programming is provided from both theoretical and performance points of view. It is shown that Reinforcement-based neural control can lead to results comparable in quality to Dynamic Programming-based though less computationnally expens...

متن کامل

An accelerated stopping rule for the Nested Partition Hybrid Algorithm for discrete stochastic optimization

A series expansion approach to risk analysis of an inventory system with sourcing. Efficient algorithm for computing the ergodic projector of Markov multi-chains. A critical account of perturbation analysis of Markovian systems. Robust analysis of single server networks with infinite supply and unreliable nodes. Other publications: J. Berkhout. Onzekerheid die ertoe doet: een aanzet tot integra...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Journal of Hydroinformatics

سال: 2016

ISSN: 1464-7141,1465-1734

DOI: 10.2166/hydro.2016.243