Study and development of reinforcement learning multiagent collaborative algorithms for solving families of problems

Baldazo Escriña, David (2017). Study and development of reinforcement learning multiagent collaborative algorithms for solving families of problems. Proyecto Fin de Carrera / Trabajo Fin de Grado, E.T.S.I. Telecomunicación (UPM), Madrid.

Description

Title: Study and development of reinforcement learning multiagent collaborative algorithms for solving families of problems
Author/s:
  • Baldazo Escriña, David
Contributor/s:
  • Zazo Bello, Santiago
Item Type: Final Project
Degree: Grado en Ingeniería de Tecnologías y Servicios de Telecomunicación
Date: 2017
Subjects:
Freetext Keywords: Artificial intelligence, reinforcement learning, dynamic programming, optimal control, transfer learning, distributed, multiagent, diffusion, Pareto optimality.
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

Artificial intelligence algorithms enable autonomous agents to perform sophisticated tasks with great accuracy. A particularly relevant technique within artificial intelligence is that of reinforcement learning, which allows strategic planning and optimal control of an environment through interaction with it and without prior knowledge. Most current algorithms based on reinforcement learning allow us to learn the optimal policy that solves a specific problem, that is, the actions performed in each state that allow maximizing the reward obtained by the agent when it interacts with a given environment. It is of great interest the study of techniques that allow to obtain policies that are suitable not only for a specific problem, but for a whole family of similar problems. This new problem is called transfer learning, where the goal is that the knowledge obtained during the resolution of a problem is useful to solve other different but related problems. The goal of this final degree project is the development of distributed reinforcement learning algorithms in which multiple agents learn different instances of a family of problems, so that each agent learns by interacting with their particular environment, but the agents communicate with each other and cooperate to learn a policy that is good for the whole family of problems. We will also develop techniques to evaluate whether these algorithms generalize in some sense the solution to any similar problem.

More information

Item ID: 47539
DC Identifier: https://oa.upm.es/47539/
OAI Identifier: oai:oa.upm.es:47539
Deposited by: Biblioteca ETSI Telecomunicación
Deposited on: 28 Aug 2017 10:24
Last Modified: 28 Aug 2017 10:24
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM