{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/simulating-emergent-properties-of-human","title":"Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning","arxiv_id":"1903.05766","date":"2019-03-14","proceeding":null,"authors":["Raunak P. Bhattacharyya","Derek J. Phillips","Changliu Liu","Jayesh K. Gupta","Katherine Driggs-Campbell","Mykel J. Kochenderfer"],"abstract":"Recent developments in multi-agent imitation learning have shown promising\nresults for modeling the behavior of human drivers. However, it is challenging\nto capture emergent traffic behaviors that are observed in real-world datasets.\nSuch behaviors arise due to the many local interactions between agents that are\nnot commonly accounted for in imitation learning. This paper proposes Reward\nAugmented Imitation Learning (RAIL), which integrates reward augmentation into\nthe multi-agent imitation learning framework and allows the designer to specify\nprior knowledge in a principled fashion. We prove that convergence guarantees\nfor the imitation learning process are preserved under the application of\nreward augmentation. This method is validated in a driving scenario, where an\nentire traffic scene is controlled by driving policies learned using our\nproposed algorithm. Further, we demonstrate improved performance in comparison\nto traditional imitation learning algorithms both in terms of the local actions\nof a single agent and the behavior of emergent properties in complex,\nmulti-agent settings.","url_abs":"http://arxiv.org/abs/1903.05766v1","url_pdf":"http://arxiv.org/pdf/1903.05766v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"simulating-emergent-properties-of-human","repo_url":"https://github.com/sisl/ngsim_env","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.05766","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}