Navigational Behavior of Humans and Deep Reinforcement Learning Agents.

Autor:	Rigoli LM; School of Psychological Sciences, Macquarie University, Sydney, NSW, Australia., Patil G; School of Psychological Sciences, Macquarie University, Sydney, NSW, Australia.; Centre for Elite Performance, Expertise and Training, Macquarie University, Sydney, NSW, Australia., Stening HF; School of Psychological Sciences, Macquarie University, Sydney, NSW, Australia., Kallen RW; School of Psychological Sciences, Macquarie University, Sydney, NSW, Australia.; Centre for Elite Performance, Expertise and Training, Macquarie University, Sydney, NSW, Australia., Richardson MJ; School of Psychological Sciences, Macquarie University, Sydney, NSW, Australia.; Centre for Elite Performance, Expertise and Training, Macquarie University, Sydney, NSW, Australia.
Jazyk:	angličtina
Zdroj:	Frontiers in psychology [Front Psychol] 2021 Sep 22; Vol. 12, pp. 725932. Date of Electronic Publication: 2021 Sep 22 (Print Publication: 2021).
DOI:	10.3389/fpsyg.2021.725932
Abstrakt:	Rapid advances in the field of Deep Reinforcement Learning (DRL) over the past several years have led to artificial agents (AAs) capable of producing behavior that meets or exceeds human-level performance in a wide variety of tasks. However, research on DRL frequently lacks adequate discussion of the low-level dynamics of the behavior itself and instead focuses on meta-level or global-level performance metrics. In doing so, the current literature lacks perspective on the qualitative nature of AA behavior, leaving questions regarding the spatiotemporal patterning of their behavior largely unanswered. The current study explored the degree to which the navigation and route selection trajectories of DRL agents (i.e., AAs trained using DRL) through simple obstacle ridden virtual environments were equivalent (and/or different) from those produced by human agents. The second and related aim was to determine whether a task-dynamical model of human route navigation could not only be used to capture both human and DRL navigational behavior, but also to help identify whether any observed differences in the navigational trajectories of humans and DRL agents were a function of differences in the dynamical environmental couplings. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2021 Rigoli, Patil, Stening, Kallen and Richardson.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu