A Machine with Short-Term, Episodic, and Semantic Memory Systems

Conference Paper (2023)
Author(s)

Taewoon Kim (Vrije Universiteit Amsterdam)

Michael Cochez (Vrije Universiteit Amsterdam)

Vincent François-Lavet (Vrije Universiteit Amsterdam)

M.A. Neerincx (TU Delft - Interactive Intelligence)

Piek Vossen (Vrije Universiteit Amsterdam)

Research Group
Interactive Intelligence
Copyright
© 2023 Taewoon Kim, Michael Cochez, Vincent François-Lavet, M.A. Neerincx, Piek Vossen
DOI related publication
https://doi.org/10.1609/aaai.v37i1.25075
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Taewoon Kim, Michael Cochez, Vincent François-Lavet, M.A. Neerincx, Piek Vossen
Research Group
Interactive Intelligence
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.@en
Pages (from-to)
48-56
ISBN (electronic)
978-157735880-0
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and analyze the behavior of this agent, we designed and released our own reinforcement learning agent environment, “the Room”, where an agent has to learn how to encode, store, and retrieve memories to maximize its return by answering questions. We show that our deep Q-learning based agent successfully learns whether a short-term memory should be forgotten, or rather be stored in the episodic or semantic memory systems. Our experiments indicate that an agent with human-like memory systems can outperform an agent without this memory structure in the environment.

Files

25075_Article_Text_29138_1_2_2... (pdf)
(pdf | 0.557 Mb)
- Embargo expired in 27-12-2023
License info not available