Blakeman, Sam and Mareschal, Denis (2022) Explanations from Deep Reinforcement Learning using episodic memories. CEUR Workshop Proceedings 3227 , pp. 53-58. ISSN 1613-0073.
|
Text
49306.pdf - Published Version of Record Available under License Creative Commons Attribution. Download (1MB) | Preview |
Abstract
Deep Reinforcement Learning (RL) involves the use of Deep Neural Networks (DNNs) to make sequential decisions in order to maximize reward. For many tasks the resulting sequence of actions produced by a Deep RL policy can be long and difficult to understand for humans. A crucial component of human explanations is selectivity, whereby only key decisions and causes are recounted. Imbuing Deep RL agents with such an ability would make their resulting policies easier to understand from a human perspective and generate a concise set of instructions to aid the learning of future agents. To this end we use a Deep RL agent with an episodic memory system to identify and recount key decisions during policy execution. We show that these decisions form a short, human readable explanation that can also be used to speed up the learning of naive Deep RL agents.
Metadata
| Item Type: | Article |
|---|---|
| Additional Information: | Proceedings of the 3rd Human-Like Computing Workshop (HLC 2022) co-located with the 2nd International Joint Conference on Learning and Reasoning (IJCLR 2022) |
| Keyword(s) / Subject(s): | Deep Reinforcement Learning, Explanation, Complementary Learning Systems, Episodic Memory |
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Psychological Sciences |
| Research Centres and Institutes: | Brain and Cognitive Development, Centre for (CBCD) |
| Depositing User: | Administrator |
| Date Deposited: | 03 Oct 2022 12:34 |
| Last Modified: | 02 Aug 2023 18:18 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/49306 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
