Toward a Psychology of Deep Reinforcement Learning Agents Using a Cognitive Architecture
No Thumbnail Available
Authors
Mitsopoulos, Konstantinos
Somers, Sterling
Schooler, Joel
Lebiere, Christian
Pirolli, Peter
Thomson, Robert
Issue Date
2021-09-01
Type
journal-article
Language
en_US
Keywords
Alternative Title
Abstract
We argue that cognitive models can provide a common ground between human users and deep reinforcement learning (Deep RL) algorithms for purposes of explainable artificial intelligence (AI). Casting both the human and learner as cognitive models provides common mechanisms to compare and understand their underlying decision-making processes. This common grounding allows us to identify divergences and explain the learner's behavior in human understandable terms. We present novel salience techniques that highlight the most relevant features in each model's decision-making, as well as examples of this technique in common training environments such as Starcraft II and an OpenAI gridworld.
Description
Citation
Mitsopoulos, K., Somers, S., Schooler, J., Lebiere, C., Pirolli, P. and Thomson, R. (2022), Toward a Psychology of Deep Reinforcement Learning Agents Using a Cognitive Architecture. Top. Cogn. Sci., 14: 756-779. https://doi.org/10.1111/tops.12573
Publisher
License
Journal
Volume
Issue
PubMed ID
ISSN
1756-8757
1756-8765
1756-8765