EPIA2019_paper_249.pdf (378.09 kB)

Spatio-temporal attention deep recurrent Q-network for POMDPs

Download (378.09 kB)
conference contribution
posted on 27.11.2019 by Mariano Etchart, Pawel Ladosz, David Mulvaney
© Springer Nature Switzerland AG 2019. One of the long-standing challenges for reinforcement learning agents is to deal with noisy environments. Although progress has been made in producing an agent capable of optimizing its environment in fully observable conditions, partial observability still remains a difficult task. In this paper, a novel model is proposed which inspired by human perception, utilizes two fundamental machine learning concepts, attention and memory, to better confront a noisy environment.

History

School

  • Mechanical, Electrical and Manufacturing Engineering
  • Science

Department

  • Computer Science

Published in

Progress in Artificial Intelligence: 19th EPIA Conference on Artificial Intelligence, EPIA 2019, Vila Real, Portugal, September 3–6, 2019, Proceedings.

Volume

Part I

Pages

98 - 105

Publisher

Springer

Version

AM (Accepted Manuscript)

Publisher statement

This is a pre-copyedited version of a contribution published in Progress in Artificial Intelligence: 19th EPIA Conference on Artificial Intelligence, EPIA 2019. edited Paulo Moura Oliveira • Paulo Novais • Luís Paulo Reis (Eds.) published by Springer. The definitive authenticated version is available online via https://doi.org/10.1007/978-3-030-30241-2_9

Publication date

2019-08-30

Copyright date

2019

ISBN

9783030302405

ISSN

0302-9743

eISSN

1611-3349

Book series

Lecture Notes in Computer Science vol 11804; Lecture Notes in Artificial Intelligence vol 11804

Language

en

Editor(s)

Paulo Moura Oliveira • Paulo Novais • Luís Paulo Reis

Location

Vila Real, Portugal

Event dates

September 3–6

Depositor

Dr David Mulvaney. Deposit date: 26 November 2019

Exports

Logo branding

Categories

Exports