Wei, R, Garcia, A, McDonald, A et al. (4 more authors) (2023) World Model Learning from Demonstrations with Active Inference: Application to Driving Behavior. In: Active Inference. Third International Workshop, IWAI 2022, 19 Sep 2022, Grenoble, France. Springer , pp. 130-142. ISBN 9783031287183
Abstract
Active inference proposes a unifying principle for perception and action as jointly minimizing the free energy of an agent’s internal world model. In the active inference literature, world models are typically pre-specified or learned through interacting with an environment. This paper explores the possibility of learning world models of active inference agents from recorded demonstrations, with an application to human driving behavior modeling. The results show that the presented method can create models that generate human-like driving behavior but the approach is sensitive to input features.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG. This version of the paper has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use (https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms), but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-28719-0_9 |
Keywords: | Active inference; Inverse reinforcement learning; Driving behavior modeling |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Environment (Leeds) > Institute for Transport Studies (Leeds) > ITS: Safety and Technology (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 05 Jul 2023 11:16 |
Last Modified: | 22 Mar 2024 01:13 |
Status: | Published |
Publisher: | Springer |
Identification Number: | 10.1007/978-3-031-28719-0_9 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:200915 |