Reflexive Reinforcement Learning: Methods for Self-Referential Autonomous Learning

B. I. Lyons, J. Michael Herrmann

2020

Abstract

Reinforcement learning aims at maximising an external evaluative signal over a certain time horizon. If no reward is available within the time horizon, the agent faces an autonomous learning task which can be used to explore, to gather information, and to bootstrap particular learning behaviours. We discuss here how the agent can use a current representation of the value, of its state and of the environment, in order to produce autonomous learning behaviour in the absence of a meaningful rewards. The family of methods that is introduced here is open to further development and research in the field of reflexive reinforcement learning.

Paper Citation

in Harvard Style

Lyons B. and Herrmann J. (2020). Reflexive Reinforcement Learning: Methods for Self-Referential Autonomous Learning. In Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - Volume 1: NCTA; ISBN 978-989-758-475-6, SciTePress, pages 381-388. DOI: 10.5220/0009997503810388

in Bibtex Style

@conference{ncta20,
author={B. I. Lyons and J. Michael Herrmann},
title={Reflexive Reinforcement Learning: Methods for Self-Referential Autonomous Learning},
booktitle={Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - Volume 1: NCTA},
year={2020},
pages={381-388},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009997503810388},
isbn={978-989-758-475-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computational Intelligence (IJCCI 2020) - Volume 1: NCTA
TI - Reflexive Reinforcement Learning: Methods for Self-Referential Autonomous Learning
SN - 978-989-758-475-6
AU - Lyons B.
AU - Herrmann J.
PY - 2020
SP - 381
EP - 388
DO - 10.5220/0009997503810388
PB - SciTePress