Using Awareness to Promote Richer, More Human-Like Behaviors in Artificial Agents

Yliniemi, Logan; Tumer, Kagan

doi:10.1007/978-3-319-46840-2_8

Cited by 1 publication

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In either case, the effectiveness of human-AA team training scenarios often depends on the ability of AAs to reciprocally adapt and respond to human co-actors in a seamless and effective manner. Indeed, for certain kinds of tasks, achieving optimal human user experience and learning depends on AA technologies incorporating natural, human-like patterns of behavior, as more human-like AAs tend to result in a better transition from AA training to realworld human team performance (Cappuccio et al, 2021;Miyashita et al, 2017;Sandoval et al, 2016Sandoval et al, , 2020Turnwald & Wollherr, 2019;Yliniemi & Tumer, 2016).…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Dynamical Perceptual-Motor Primitives and Deep Reinforcement Learning for Human-Artificial Agent Training Systems

Rigoli

Patil

Nalepka

et al. 2022

Journal of Cognitive Engineering and Decision Making

View full text Add to dashboard Cite

Effective team performance often requires that individuals engage in team training exercises. However, organizing team-training scenarios presents economic and logistical challenges and can be prone to trainer bias and fatigue. Accordingly, a growing body of research is investigating the effectiveness of employing artificial agents (AAs) as synthetic teammates in team training simulations, and, relatedly, how to best develop AAs capable of robust, human-like behavioral interaction. Motivated by these challenges, the current study examined whether task dynamical models of expert human herding behavior could be embedded in the control architecture of AAs to train novice actors to perform a complex multiagent herding task. Training outcomes were compared to human-expert trainers, novice baseline performance, and AAs developed using deep reinforcement learning (DRL). Participants’ subjective preferences for the AAs developed using DRL or dynamical models of human performance were also investigated. The results revealed that AAs controlled by dynamical models of human expert performance could train novice actors at levels equivalent to expert human trainers and were also preferred over AAs developed using DRL. The implications for the development of AAs for robust human-AA interaction and training are discussed, including the potential benefits of employing hybrid Dynamical-DRL techniques for AA development.

show abstract