{"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/model-predictive-policy-learning-with","title":"Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic","arxiv_id":"1901.02705","date":"2019-01-08","proceeding":"ICLR 2019 5","authors":["Mikael Henaff","Alfredo Canziani","Yann Lecun"],"abstract":"Learning a policy using only observational data is challenging because the\ndistribution of states it induces at execution time may differ from the\ndistribution observed during training. We propose to train a policy by\nunrolling a learned model of the environment dynamics over multiple time steps\nwhile explicitly penalizing two costs: the original cost the policy seeks to\noptimize, and an uncertainty cost which represents its divergence from the\nstates it is trained on. We measure this second cost by using the uncertainty\nof the dynamics model about its own predictions, using recent ideas from\nuncertainty estimation for deep networks. We evaluate our approach using a\nlarge-scale observational dataset of driving behavior recorded from traffic\ncameras, and show that we are able to learn effective driving policies from\npurely observational data, with no environment interaction.","url_abs":"http://arxiv.org/abs/1901.02705v1","url_pdf":"http://arxiv.org/pdf/1901.02705v1.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":"model-predictive-policy-learning-with","repo_url":"https://github.com/Atcold/pytorch-PPUU","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"unrolling","task_name":"Rolling Shutter Correction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.02705","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}