{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T23:04:49Z","timestamp":1782774289574,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020YFE0200500"],"award-info":[{"award-number":["2020YFE0200500"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,11]]},"DOI":"10.1145\/3488560.3498438","type":"proceedings-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T21:42:57Z","timestamp":1644961377000},"page":"648-656","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["RLMob"],"prefix":"10.1145","author":[{"given":"Ziyan","family":"Luo","sequence":"first","affiliation":[{"name":"Mila, McGill University, Montreal, PQ, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congcong","family":"Miao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2016.7738886"},{"key":"e_1_3_2_2_2_1","volume-title":"Program Synthesis Using Deduction-Guided Reinforcement Learning","author":"Chen Yanju","unstructured":"Yanju Chen, Chenglong Wang, Osbert Bastani, Isil Dillig, and Yu Feng. 2020. Program Synthesis Using Deduction-Guided Reinforcement Learning. In Computer Aided Verification, Shuvendu K. Lahiri and Chao Wang (Eds.). Springer International Publishing, Cham, 587--610."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17504"},{"key":"e_1_3_2_2_4_1","volume-title":"Dzmitry Bahdanau, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart Van Merri\u00ebnboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Jie Feng Yong Li Chao Zhang Funing Sun Fanchao Meng Ang Guo and Depeng Jin. 2018. DeepMove: Predicting Human Mobility with Attentional Recurrent Networks. (2018) 1459--1468.","DOI":"10.1145\/3178876.3186058"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the First Workshop on Measurement, Privacy, and Mobility. ACM, 3.","author":"Gambs S\u00e9bastien","unstructured":"S\u00e9bastien Gambs, Marc-Olivier Killijian, and Miguel N\u00fa nez del Prado Cortez. 2012. Next place prediction using mobility markov chains. In Proceedings of the First Workshop on Measurement, Privacy, and Mobility. ACM, 3."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Qiang Gao Fan Zhou Goce Trajcevski Kunpeng Zhang Ting Zhong and Fengli Zhang. 2019. Predicting Human Mobility via Variational Attention. (2019) 2750--2756.","DOI":"10.1145\/3308558.3313610"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Qiang Gao Fan Zhou Kunpeng Zhang Goce Trajcevski Xucheng Luo and Fengli Zhang. 2017. Identifying human mobility via trajectory embeddings. (2017) 1689--1695.","DOI":"10.24963\/ijcai.2017\/234"},{"key":"e_1_3_2_2_9_1","volume-title":"Memory-based control with recurrent neural networks. arXiv preprint arXiv:1512.04455","author":"Heess Nicolas","year":"2015","unstructured":"Nicolas Heess, Jonathan J Hunt, Timothy P Lillicrap, and David Silver. 2015. Memory-based control with recurrent neural networks. arXiv preprint arXiv:1512.04455 (2015)."},{"key":"e_1_3_2_2_10_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_2_11_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation , Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_2_12_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623638"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487673"},{"key":"e_1_3_2_2_15_1","volume-title":"Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts. In Thirtieth Aaai Conference on Artificial Intelligence .","author":"Liu Qiang","year":"2016","unstructured":"Qiang Liu, Shu Wu, Liang Wang, and Tieniu Tan. 2016. Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts. In Thirtieth Aaai Conference on Artificial Intelligence ."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449862"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370421"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371846"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3398761.3398864"},{"key":"e_1_3_2_2_20_1","volume-title":"International conference on machine learning . 1889--1897","author":"Schulman John","year":"2015","unstructured":"John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz. 2015. Trust region policy optimization. In International conference on machine learning . 1889--1897."},{"key":"e_1_3_2_2_21_1","volume-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation. CoRR","author":"Schulman John","year":"2016","unstructured":"John Schulman, Philipp Moritz, Sergey Levine, Michael I. Jordan, and Pieter Abbeel. 2016. High-Dimensional Continuous Control Using Generalized Advantage Estimation. CoRR , Vol. abs\/1506.02438 (2016)."},{"key":"e_1_3_2_2_22_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975673.87"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2916577"},{"key":"e_1_3_2_2_26_1","volume-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning","author":"Williams Ronald J","year":"1992","unstructured":"Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning , Vol. 8, 3--4 (1992), 229--256."},{"key":"e_1_3_2_2_27_1","volume-title":"A learning algorithm for continually running fully recurrent neural networks. Neural computation","author":"Williams Ronald J","year":"1989","unstructured":"Ronald J Williams and David Zipser. 1989. A learning algorithm for continually running fully recurrent neural networks. Neural computation , Vol. 1, 2 (1989), 270--280."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2327053"},{"key":"e_1_3_2_2_29_1","unstructured":"Junbo Zhang Yu Zheng and Dekang Qi. 2016. Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction. (2016) 1655--1661."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2743025"}],"event":{"name":"WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining","location":"Virtual Event AZ USA","acronym":"WSDM '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498438","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488560.3498438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:51Z","timestamp":1750191531000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498438"}},"subtitle":["Deep Reinforcement Learning for Successive Mobility Prediction"],"short-title":[],"issued":{"date-parts":[[2022,2,11]]},"references-count":30,"alternative-id":["10.1145\/3488560.3498438","10.1145\/3488560"],"URL":"https:\/\/doi.org\/10.1145\/3488560.3498438","relation":{},"subject":[],"published":{"date-parts":[[2022,2,11]]},"assertion":[{"value":"2022-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}