{"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/urban-driving-with-multi-objective-deep","title":"Urban Driving with Multi-Objective Deep Reinforcement Learning","arxiv_id":"1811.08586","date":"2018-11-21","proceeding":null,"authors":["Changjian Li","Krzysztof Czarnecki"],"abstract":"Autonomous driving is a challenging domain that entails multiple aspects: a\nvehicle should be able to drive to its destination as fast as possible while\navoiding collision, obeying traffic rules and ensuring the comfort of\npassengers. In this paper, we present a deep learning variant of thresholded\nlexicographic Q-learning for the task of urban driving. Our multi-objective DQN\nagent learns to drive on multi-lane roads and intersections, yielding and\nchanging lanes according to traffic rules. We also propose an extension for\nfactored Markov Decision Processes to the DQN architecture that provides\nauxiliary features for the Q function. This is shown to significantly improve\ndata efficiency. We then show that the learned policy is able to zero-shot\ntransfer to a ring road without sacrificing performance.","url_abs":"http://arxiv.org/abs/1811.08586v2","url_pdf":"http://arxiv.org/pdf/1811.08586v2.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":"urban-driving-with-multi-objective-deep","repo_url":"https://gitlab.com/sumo-rl/sumo_openai_gym","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.08586","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}