{"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/simultaneous-policy-learning-and-latent-state","title":"Simultaneous Policy Learning and Latent State Inference for Imitating Driver Behavior","arxiv_id":"1704.05566","date":"2017-04-19","proceeding":null,"authors":["Jeremy Morton","Mykel J. Kochenderfer"],"abstract":"In this work, we propose a method for learning driver models that account for\nvariables that cannot be observed directly. When trained on a synthetic\ndataset, our models are able to learn encodings for vehicle trajectories that\ndistinguish between four distinct classes of driver behavior. Such encodings\nare learned without any knowledge of the number of driver classes or any\nobjective that directly requires the models to learn encodings for each class.\nWe show that driving policies trained with knowledge of latent variables are\nmore effective than baseline methods at imitating the driver behavior that they\nare trained to replicate. Furthermore, we demonstrate that the actions chosen\nby our policy are heavily influenced by the latent variable settings that are\nprovided to them.","url_abs":"http://arxiv.org/abs/1704.05566v1","url_pdf":"http://arxiv.org/pdf/1704.05566v1.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":"simultaneous-policy-learning-and-latent-state","repo_url":"https://github.com/sisl/latent_driver","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"simultaneous-policy-learning-and-latent-state","repo_url":"https://github.com/Shuijing725/VAE_trait_inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}