{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:00:09Z","timestamp":1780516809925,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671823","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"4512-4523","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3370-7828","authenticated-orcid":false,"given":"Xinbo","family":"Zhao","sequence":"first","affiliation":[{"name":"Binghamton University, Binghamton, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0947-1875","authenticated-orcid":false,"given":"Yingxue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Binghamton University, Binghamton, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0289-1452","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"San Diego State University, San Diego, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1627-5503","authenticated-orcid":false,"given":"Yu","family":"Yang","sequence":"additional","affiliation":[{"name":"Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6439-1333","authenticated-orcid":false,"given":"Yiqun","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8972-503X","authenticated-orcid":false,"given":"Yanhua","family":"Li","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2032-0381","authenticated-orcid":false,"given":"Jun","family":"Luo","sequence":"additional","affiliation":[{"name":"Logistics and Supply Chain MultiTech R&D Centre, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2024. MOTSC: Model-based Offline Traffic Signal Control. https:\/\/openreview. net\/forum?id=K6BXvqWWmq"},{"key":"e_1_3_2_2_2_1","volume-title":"Hindsight Experience Replay. CoRR abs\/1707.01495","author":"Andrychowicz Marcin","year":"2017","unstructured":"Marcin Andrychowicz, FilipWolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, Pieter Abbeel, and Wojciech Zaremba. 2017. Hindsight Experience Replay. CoRR abs\/1707.01495 (2017). arXiv:1707.01495 http:\/\/arxiv.org\/abs\/1707.01495"},{"key":"e_1_3_2_2_3_1","unstructured":"Samy Bengio Oriol Vinyals Navdeep Jaitly and Noam Shazeer. 2015. Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks. arXiv:1506.03099 [cs.LG]"},{"key":"e_1_3_2_2_4_1","volume-title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills. CoRR abs\/2104.07749","author":"Chebotar Yevgen","year":"2021","unstructured":"Yevgen Chebotar, Karol Hausman, Yao Lu, Ted Xiao, Dmitry Kalashnikov, Jake Varley, Alex Irpan, Benjamin Eysenbach, Ryan Julian, Chelsea Finn, and Sergey Levine. 2021. Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills. CoRR abs\/2104.07749 (2021). arXiv:2104.07749 https:\/\/arxiv. org\/abs\/2104.07749"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CAC53003.2021"},{"key":"e_1_3_2_2_6_1","volume-title":"Advances in Neural Information Processing Systems","author":"Dorfman Ron","year":"2021","unstructured":"Ron Dorfman, Idan Shenfeld, and Aviv Tamar. 2021. Offline Meta Reinforcement Learning -- Identifiability Challenges and Effective Data Collection Strategies. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 4607--4618. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/ file\/248024541dbda1d3fd75fe49d1a4df4d-Paper.pdf"},{"key":"e_1_3_2_2_7_1","volume-title":"Tree-Based Batch Mode Reinforcement Learning. J. Mach. Learn. Res. 6 (dec","author":"Ernst Damien","year":"2005","unstructured":"Damien Ernst, Pierre Geurts, and Louis Wehenkel. 2005. Tree-Based Batch Mode Reinforcement Learning. J. Mach. Learn. Res. 6 (dec 2005), 503--556."},{"key":"e_1_3_2_2_8_1","volume-title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement. CoRR abs\/2002.11089","author":"Eysenbach Benjamin","year":"2020","unstructured":"Benjamin Eysenbach, Xinyang Geng, Sergey Levine, and Ruslan Salakhutdinov. 2020. Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement. CoRR abs\/2002.11089 (2020). arXiv:2002.11089 https:\/\/arxiv.org\/abs\/2002. 11089"},{"key":"e_1_3_2_2_9_1","volume-title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement. CoRR abs\/2002.11089","author":"Eysenbach Benjamin","year":"2020","unstructured":"Benjamin Eysenbach, Xinyang Geng, Sergey Levine, and Ruslan Salakhutdinov. 2020. Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement. CoRR abs\/2002.11089 (2020). arXiv:2002.11089 https:\/\/arxiv.org\/abs\/2002. 11089"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning -","volume":"70","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In Proceedings of the 34th International Conference on Machine Learning - Volume 70. 1126--1135."},{"key":"e_1_3_2_2_11_1","volume-title":"Off-Policy Deep Reinforcement Learning without Exploration. CoRR abs\/1812.02900","author":"Fujimoto Scott","year":"2018","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2018. Off-Policy Deep Reinforcement Learning without Exploration. CoRR abs\/1812.02900 (2018). arXiv:1812.02900 http:\/\/arxiv.org\/abs\/1812.02900"},{"key":"e_1_3_2_2_12_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative Adversarial Nets. In NeurIPS."},{"key":"e_1_3_2_2_13_1","unstructured":"Tuomas Haarnoja Aurick Zhou Pieter Abbeel and Sergey Levine. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. arXiv:1801.01290 [cs.LG]"},{"key":"e_1_3_2_2_14_1","volume-title":"Multi-task deep reinforcement learning with popart. arXiv preprint arXiv:1901.04465","author":"Hessel Matteo","year":"2019","unstructured":"Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Azar, and David Silver. 2019. Multi-task deep reinforcement learning with popart. arXiv preprint arXiv:1901.04465 (2019)."},{"key":"e_1_3_2_2_15_1","volume-title":"Generative adversarial imitation learning. Advances in neural information processing systems 29","author":"Ho Jonathan","year":"2016","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_2_16_1","volume-title":"Craig Ferguson, \u00c0gata Lapedriza, Noah Jones, Shixiang Gu, and RosalindW. Picard.","author":"Jaques Natasha","year":"2019","unstructured":"Natasha Jaques,Asma Ghandeharioun, Judy Hanwen Shen, Craig Ferguson, \u00c0gata Lapedriza, Noah Jones, Shixiang Gu, and RosalindW. Picard. 2019. Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog. CoRR abs\/1907.00456 (2019). arXiv:1907.00456 http:\/\/arxiv.org\/abs\/1907.00456"},{"key":"e_1_3_2_2_17_1","volume-title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation. CoRR abs\/1806.10293","author":"Kalashnikov Dmitry","year":"2018","unstructured":"Dmitry Kalashnikov, Alex Irpan, Peter Pastor, Julian Ibarz, Alexander Herzog, Eric Jang, Deirdre Quillen, Ethan Holly, Mrinal Kalakrishnan, Vincent Vanhoucke, and Sergey Levine. 2018. QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation. CoRR abs\/1806.10293 (2018). arXiv:1806.10293 http:\/\/arxiv.org\/abs\/1806.10293"},{"key":"e_1_3_2_2_18_1","volume-title":"MTOpt: Continuous Multi-Task Robotic Reinforcement Learning at Scale. CoRR abs\/2104.08212","author":"Kalashnikov Dmitry","year":"2021","unstructured":"Dmitry Kalashnikov, Jacob Varley, Yevgen Chebotar, Benjamin Swanson, Rico Jonschkowski, Chelsea Finn, Sergey Levine, and Karol Hausman. 2021. MTOpt: Continuous Multi-Task Robotic Reinforcement Learning at Scale. CoRR abs\/2104.08212 (2021). arXiv:2104.08212 https:\/\/arxiv.org\/abs\/2104.08212"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Kidambi Rahul","year":"2020","unstructured":"Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli, and Thorsten Joachims. 2020. MOReL: Model-Based Offline Reinforcement Learning. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS'20). Curran Associates Inc., Red Hook, NY, USA, Article 1830, 14 pages."},{"key":"e_1_3_2_2_20_1","volume-title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization. CoRR abs\/2103.08050","author":"Kostrikov Ilya","year":"2021","unstructured":"Ilya Kostrikov, Jonathan Tompson, Rob Fergus, and Ofir Nachum. 2021. Offline Reinforcement Learning with Fisher Divergence Critic Regularization. CoRR abs\/2103.08050 (2021). arXiv:2103.08050 https:\/\/arxiv.org\/abs\/2103.08050"},{"key":"e_1_3_2_2_21_1","volume-title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction. CoRR abs\/1906.00949","author":"Kumar Aviral","year":"2019","unstructured":"Aviral Kumar, Justin Fu, George Tucker, and Sergey Levine. 2019. Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction. CoRR abs\/1906.00949 (2019). arXiv:1906.00949 http:\/\/arxiv.org\/abs\/1906.00949"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3495824"},{"key":"e_1_3_2_2_23_1","volume-title":"Offline Reinforcement Learning for Road Traffic Control. CoRR abs\/2201.02381","author":"Kunjir Mayuresh","year":"2022","unstructured":"Mayuresh Kunjir and Sanjay Chawla. 2022. Offline Reinforcement Learning for Road Traffic Control. CoRR abs\/2201.02381 (2022). arXiv:2201.02381 https: \/\/arxiv.org\/abs\/2201.02381"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--642--27645--3_2"},{"key":"e_1_3_2_2_25_1","volume-title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. CoRR abs\/2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems. CoRR abs\/2005.01643 (2020). arXiv:2005.01643 https:\/\/arxiv.org\/abs\/2005.01643"},{"key":"e_1_3_2_2_26_1","unstructured":"Jianxiong Li Shichao Lin Tianyu Shi Chujie Tian Yu Mei Jian Song Xianyuan Zhan and Ruimin Li. 2023. A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning. arXiv:2311.15920 [cs.AI]"},{"key":"e_1_3_2_2_27_1","volume-title":"Harjatin Singh Baweja, and David Held","author":"Lin Xingyu","year":"2019","unstructured":"Xingyu Lin, Harjatin Singh Baweja, and David Held. 2019. Reinforcement Learning without Ground-Truth State. CoRR abs\/1905.07866 (2019). arXiv:1905.07866 http:\/\/arxiv.org\/abs\/1905.07866"},{"key":"e_1_3_2_2_28_1","volume-title":"Competitive Experience Replay. CoRR abs\/1902.00528","author":"Liu Hao","year":"2019","unstructured":"Hao Liu, Alexander Trott, Richard Socher, and Caiming Xiong. 2019. Competitive Experience Replay. CoRR abs\/1902.00528 (2019). arXiv:1902.00528 http:\/\/arxiv. org\/abs\/1902.00528"},{"key":"e_1_3_2_2_29_1","volume-title":"Sergey Levine, and Chelsea Finn.","author":"Mitchell Eric","year":"2020","unstructured":"Eric Mitchell, Rafael Rafailov, Xue Bin Peng, Sergey Levine, and Chelsea Finn. 2020. Offline Meta-Reinforcement Learning with Advantage Weighting. CoRR abs\/2008.06043 (2020). arXiv:2008.06043 https:\/\/arxiv.org\/abs\/2008.06043"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403186"},{"key":"e_1_3_2_2_31_1","volume-title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning. CoRR abs\/1910.00177","author":"Peng Xue Bin","year":"2019","unstructured":"Xue Bin Peng, Aviral Kumar, Grace Zhang, and Sergey Levine. 2019. Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning. CoRR abs\/1910.00177 (2019). arXiv:1910.00177 http:\/\/arxiv.org\/abs\/1910.00177"},{"key":"e_1_3_2_2_32_1","volume-title":"Offline Meta-Reinforcement Learning with Online Self-Supervision. CoRR abs\/2107.03974","author":"Pong Vitchyr H.","year":"2021","unstructured":"Vitchyr H. Pong, Ashvin Nair, Laura M. Smith, Catherine Huang, and Sergey Levine. 2021. Offline Meta-Reinforcement Learning with Online Self-Supervision. CoRR abs\/2107.03974 (2021). arXiv:2107.03974 https:\/\/arxiv.org\/abs\/2107.03974"},{"key":"e_1_3_2_2_33_1","volume-title":"Offline Reinforcement Learning from Images with Latent Space Models. CoRR abs\/2012.11547","author":"Rafailov Rafael","year":"2020","unstructured":"Rafael Rafailov, Tianhe Yu, Aravind Rajeswaran, and Chelsea Finn. 2020. Offline Reinforcement Learning from Images with Latent Space Models. CoRR abs\/2012.11547 (2020). arXiv:2012.11547 https:\/\/arxiv.org\/abs\/2012.11547"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_2_35_1","volume-title":"Offline Reinforcement Learning for Visual Navigation. In 6th Annual Conference on Robot Learning. https:\/\/openreview.net\/forum?id= uhIfIEIiWm_","author":"Shah Dhruv","year":"2022","unstructured":"Dhruv Shah, Arjun Bhorkar, Hrishit Leen, Ilya Kostrikov, Nicholas Rhinehart, and Sergey Levine. 2022. Offline Reinforcement Learning for Visual Navigation. In 6th Annual Conference on Robot Learning. https:\/\/openreview.net\/forum?id= uhIfIEIiWm_"},{"key":"e_1_3_2_2_36_1","volume-title":"Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement. CoRR abs\/2110.07067","author":"Shi Tianyu","year":"2021","unstructured":"Tianyu Shi, Dong Chen, Kaian Chen, and Zhaojian Li. 2021. Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement. CoRR abs\/2110.07067 (2021). arXiv:2110.07067 https:\/\/arxiv.org\/abs\/2110.07067"},{"key":"e_1_3_2_2_37_1","volume-title":"Felix Berkenkamp, Abbas Abdolmaleki, Michael Neunert, Thomas Lampe, Roland Hafner, Nicolas Heess, and Martin A. Riedmiller.","author":"Siegel Noah Y.","year":"2020","unstructured":"Noah Y. Siegel, Jost Tobias Springenberg, Felix Berkenkamp, Abbas Abdolmaleki, Michael Neunert, Thomas Lampe, Roland Hafner, Nicolas Heess, and Martin A. Riedmiller. 2020. Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning. CoRR abs\/2002.08396 (2020). arXiv:2002.08396 https:\/\/arxiv.org\/abs\/2002.08396"},{"key":"e_1_3_2_2_38_1","volume-title":"Policy Continuation with Hindsight Inverse Dynamics. CoRR abs\/1910.14055","author":"Sun Hao","year":"2019","unstructured":"Hao Sun, Zhizhong Li, Xiaotong Liu, Dahua Lin, and Bolei Zhou. 2019. Policy Continuation with Hindsight Inverse Dynamics. CoRR abs\/1910.14055 (2019). arXiv:1910.14055 http:\/\/arxiv.org\/abs\/1910.14055"},{"key":"e_1_3_2_2_39_1","volume-title":"Deep multi-task learning with low level tasks supervised at lower layers. arXiv preprint arXiv:1704.05098","author":"Tessler Chen","year":"2017","unstructured":"Chen Tessler, Shahar Givony, Tom Zahavy, Daniel J Mankowitz, and Shie Mannor. 2017. Deep multi-task learning with low level tasks supervised at lower layers. arXiv preprint arXiv:1704.05098 (2017)."},{"key":"e_1_3_2_2_40_1","volume-title":"CoRR","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. CoRR (2017)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9590"},{"key":"e_1_3_2_2_42_1","volume-title":"Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation. CoRR abs\/1807.01473","author":"Wang Lu","year":"2018","unstructured":"Lu Wang, Wei Zhang, Xiaofeng He, and Hongyuan Zha. 2018. Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation. CoRR abs\/1807.01473 (2018). arXiv:1807.01473 http: \/\/arxiv.org\/abs\/1807.01473"},{"key":"e_1_3_2_2_43_1","volume-title":"Behavior Regularized Offline Reinforcement Learning. CoRR abs\/1911.11361","author":"Wu Yifan","year":"2019","unstructured":"Yifan Wu, George Tucker, and Ofir Nachum. 2019. Behavior Regularized Offline Reinforcement Learning. CoRR abs\/1911.11361 (2019). arXiv:1911.11361 http: \/\/arxiv.org\/abs\/1911.11361"},{"key":"e_1_3_2_2_44_1","volume-title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning. CoRR abs\/2202.01741","author":"Yu Tianhe","year":"2022","unstructured":"Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Chelsea Finn, and Sergey Levine. 2022. How to Leverage Unlabeled Data in Offline Reinforcement Learning. CoRR abs\/2202.01741 (2022). arXiv:2202.01741 https:\/\/arxiv.org\/abs\/ 2202.01741"},{"key":"e_1_3_2_2_45_1","volume-title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning. CoRR abs\/2109.08128","author":"Yu Tianhe","year":"2021","unstructured":"Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, and Chelsea Finn. 2021. Conservative Data Sharing for Multi-Task Offline Reinforcement Learning. CoRR abs\/2109.08128 (2021). arXiv:2109.08128 https: \/\/arxiv.org\/abs\/2109.08128"},{"key":"e_1_3_2_2_46_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Yu Tianhe","year":"2020","unstructured":"Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Y Zou, Sergey Levine, Chelsea Finn, and Tengyu Ma. 2020. MOPO: Model-based Offline Policy Optimization. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 14129--14142."},{"key":"e_1_3_2_2_47_1","volume-title":"cGAIL: Conditional Generative Adversarial Imitation Learning-An Application in Taxi Drivers' Strategy Learning","author":"Zhang Xin","year":"2020","unstructured":"Xin Zhang, Yanhua Li, Xun Zhou, and Jun Luo. 2020. cGAIL: Conditional Generative Adversarial Imitation Learning-An Application in Taxi Drivers' Strategy Learning. IEEE TBD (2020)."},{"key":"e_1_3_2_2_48_1","volume-title":"TrajGAIL: Trajectory Generative Adversarial Imitation Learning for Long-Term Decision Analysis. In ICDM'20","author":"Zhang Xin","year":"2020","unstructured":"Xin Zhang, Yanhua Li, Xun Zhou, Ziming Zhang, and Jun Luo. 2020. TrajGAIL: Trajectory Generative Adversarial Imitation Learning for Long-Term Decision Analysis. In ICDM'20."},{"key":"e_1_3_2_2_49_1","volume-title":"STMGAIL: Spatial-Temporal Meta-GAIL for Learning Diverse Human Driving Strategies.","author":"Zhang Yingxue","year":"2023","unstructured":"Yingxue Zhang, Yanhua Li, Xun Zhou, Ziming Zhang, and Jun Luo. 2023. STMGAIL: Spatial-Temporal Meta-GAIL for Learning Diverse Human Driving Strategies."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671823","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:14Z","timestamp":1750291454000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671823"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":49,"alternative-id":["10.1145\/3637528.3671823","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671823","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}