Seminari
15 giugno 2017

FEEM-IEFE Joint Seminar on "Multiobjective Evolutionary Direct Policy Search: a flexible and robust approach to solve complex water resources operation design problems"


Dove: Milan
Sede:

Fondazione Eni Enrico Mattei
Corso Magenta 63
20123 Milan

***
Video-conference
at FEEM Venice

Come raggiungere: Mappa di Google
Orario dell'evento:

h. 12.30 Seminar
In Milan a light lunch will follow the seminar for registered participants.

Informazione:

Registration is required. Please confirm your participation here.
The seminar will be broadcasted via GoToMeeting.
Seminars Office, seminars@feem.it

Speakers:

Andrea Castelletti, Politecnico di Milano, ETH Zurich

Abstract

The optimal operation of water resources systems is a wide and challenging application domain for optimal control methods and tools. Water resources systems are highly non linear systems, with large dimensional state and control spaces, affected by uncertainty and characterized by multiple competing objectives.  Most of the operational problems involving these systems can be formulated as Markov decision processes and solved via Dynamic Programming (DP) or Reinforcement Learning. Although DP family methods can be applied under mild assumptions, they suffer from three well known curses, considerably constraining their wide application: i) the curse of dimensionality, namely the computational cost of DP grows exponentially with state and control space; ii) the curse of modeling, meaning the compulsory use of in-line model-based computations that make impossible the direct, model-free inclusion of exogenous information into the controller and/ or coupling DP with process-based simulation models; iii) the curse of multiple objectives, i.e. the computational effort grows factorially with the number of objectives considered. Direct Policy Search (DPS) methods have recently emerged as a flexible tool to overcome DP’s curses. DPS is a simulation-based optimization approach, where the optimal operating policy is searched for in a given class of parameterized functions, possibly non-linear approximating networks, and the control problem transformed into a more traditional optimization problem in the policy parameters’ space. In this talk, I will review the most recent advances in Evolutionary Multi-Objective Direct Policy Search (EMODPS), by presenting a diagnostic framework for the design and the evaluation of multipurpose reservoir operations, the development of efficient EMODPS parallelization schemes, and the applications of EMODPS to a range of real world problems, including robust design under global change and rival problem framings.


***
This seminar has been jointly organized by FEEM and IEFE, Bocconi University.

Download file
Scarica il file PDF
How to reach
Download file
Scarica il file PDF
Multiobjective Evolutionary Direct Policy Search: a flexible and robust approach to solve complex water resources operation design problems

FEEM Update

Iscriviti per rimanere aggiornato.

I Suoi dati saranno trattati dalla Fondazione Eni Enrico Mattei. – Titolare del trattamento – per ricevere via posta elettronica la newsletter della Fondazione. Il conferimento dell’indirizzo e-mail è necessario alla fornitura del servizio. La invitiamo a consultare la Privacy Policy per ottenere maggiori informazioni a tutela dei Suoi diritti.

Questo Sito utilizza cookie tecnici e analytics, nonché consente l’invio di cookie di profilazione di terze parti.
Chiudendo questo banner o comunque proseguendo la navigazione sul Sito manifesti il tuo consenso all’uso dei cookie. Per ulteriori informazioni e per esprimere scelte selettive in ordine all’uso dei cookie vedi la   Cookie PolicyOk