Guardado en:
Detalles Bibliográficos
Autores principales: Takagi, Yoshiki, Tabalba, Roderick, Kirshenbaum, Nurit, Leigh, Jason
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2402.07928
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929241870827520
author Takagi, Yoshiki
Tabalba, Roderick
Kirshenbaum, Nurit
Leigh, Jason
author_facet Takagi, Yoshiki
Tabalba, Roderick
Kirshenbaum, Nurit
Leigh, Jason
contents Explainable AI (XAI) has demonstrated the potential to help reinforcement learning (RL) practitioners to understand how RL models work. However, XAI for users who do not have RL expertise (non-RL experts), has not been studied sufficiently. This results in a difficulty for the non-RL experts to participate in the fundamental discussion of how RL models should be designed for an incoming society where humans and AI coexist. Solving such a problem would enable RL experts to communicate with the non-RL experts in producing machine learning solutions that better fit our society. We argue that abstracted trajectories, that depicts transitions between the major states of the RL model, will be useful for non-RL experts to build a mental model of the agents. Our early results suggest that by leveraging a visualization of the abstracted trajectories, users without RL expertise are able to infer the behavior patterns of RL.
format Preprint
id arxiv_https___arxiv_org_abs_2402_07928
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Abstracted Trajectory Visualization for Explainability in Reinforcement Learning
Takagi, Yoshiki
Tabalba, Roderick
Kirshenbaum, Nurit
Leigh, Jason
Human-Computer Interaction
Artificial Intelligence
Machine Learning
Explainable AI (XAI) has demonstrated the potential to help reinforcement learning (RL) practitioners to understand how RL models work. However, XAI for users who do not have RL expertise (non-RL experts), has not been studied sufficiently. This results in a difficulty for the non-RL experts to participate in the fundamental discussion of how RL models should be designed for an incoming society where humans and AI coexist. Solving such a problem would enable RL experts to communicate with the non-RL experts in producing machine learning solutions that better fit our society. We argue that abstracted trajectories, that depicts transitions between the major states of the RL model, will be useful for non-RL experts to build a mental model of the agents. Our early results suggest that by leveraging a visualization of the abstracted trajectories, users without RL expertise are able to infer the behavior patterns of RL.
title Abstracted Trajectory Visualization for Explainability in Reinforcement Learning
topic Human-Computer Interaction
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.07928