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.
|Title of host publication
|AAAI-23 Technical Tracks 1
|Brian Williams, Yiling Chen, Jennifer Neville
|American Association for Artificial Intelligence (AAAI)
|Number of pages
|Published - 2023
|37th AAAI Conference on Artificial Intelligence, AAAI 2023 - Washington, United States
Duration: 7 Feb 2023 → 14 Feb 2023
|Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
|37th AAAI Conference on Artificial Intelligence, AAAI 2023
|7/02/23 → 14/02/23
Bibliographical noteGreen 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.