Search dblp for Publications

export results for "Qingpeng Cai"

 download as .bib file

@article{DBLP:journals/pvldb/CaiZJOY24,
  author       = {Qingpeng Cai and
                  Kaiping Zheng and
                  H. V. Jagadish and
                  Beng Chin Ooi and
                  James Wei Luen Yip},
  title        = {CohortNet: Empowering Cohort Discovery for Interpretable Healthcare
                  Analytics},
  journal      = {Proc. {VLDB} Endow.},
  volume       = {17},
  number       = {10},
  pages        = {2487--2500},
  year         = {2024},
  url          = {https://www.vldb.org/pvldb/vol17/p2487-cai.pdf},
  timestamp    = {Thu, 19 Sep 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/pvldb/CaiZJOY24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/Liu0YX0Z0HLJ24,
  author       = {Ziru Liu and
                  Shuchang Liu and
                  Bin Yang and
                  Zhenghai Xue and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Zijian Zhang and
                  Lantao Hu and
                  Han Li and
                  Peng Jiang},
  editor       = {Ricardo Baeza{-}Yates and
                  Francesco Bonchi},
  title        = {Modeling User Retention through Generative Flow Networks},
  booktitle    = {Proceedings of the 30th {ACM} {SIGKDD} Conference on Knowledge Discovery
                  and Data Mining, {KDD} 2024, Barcelona, Spain, August 25-29, 2024},
  pages        = {5497--5508},
  publisher    = {{ACM}},
  year         = {2024},
  url          = {https://doi.org/10.1145/3637528.3671531},
  doi          = {10.1145/3637528.3671531},
  timestamp    = {Sun, 08 Sep 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/kdd/Liu0YX0Z0HLJ24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/Wang0W0HLJGX24,
  author       = {Xiaobei Wang and
                  Shuchang Liu and
                  Xueliang Wang and
                  Qingpeng Cai and
                  Lantao Hu and
                  Han Li and
                  Peng Jiang and
                  Kun Gai and
                  Guangming Xie},
  editor       = {Ricardo Baeza{-}Yates and
                  Francesco Bonchi},
  title        = {Future Impact Decomposition in Request-level Recommendations},
  booktitle    = {Proceedings of the 30th {ACM} {SIGKDD} Conference on Knowledge Discovery
                  and Data Mining, {KDD} 2024, Barcelona, Spain, August 25-29, 2024},
  pages        = {5905--5916},
  publisher    = {{ACM}},
  year         = {2024},
  url          = {https://doi.org/10.1145/3637528.3671506},
  doi          = {10.1145/3637528.3671506},
  timestamp    = {Sun, 08 Sep 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/kdd/Wang0W0HLJGX24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigir/00010P0H00YY24,
  author       = {Qingpeng Cai and
                  Xiangyu Zhao and
                  Ling Pan and
                  Xin Xin and
                  Jin Huang and
                  Weinan Zhang and
                  Li Zhao and
                  Dawei Yin and
                  Grace Hui Yang},
  editor       = {Grace Hui Yang and
                  Hongning Wang and
                  Sam Han and
                  Claudia Hauff and
                  Guido Zuccon and
                  Yi Zhang},
  title        = {AgentIR: 1st Workshop on Agent-based Information Retrieval},
  booktitle    = {Proceedings of the 47th International {ACM} {SIGIR} Conference on
                  Research and Development in Information Retrieval, {SIGIR} 2024, Washington
                  DC, USA, July 14-18, 2024},
  pages        = {3025--3028},
  publisher    = {{ACM}},
  year         = {2024},
  url          = {https://doi.org/10.1145/3626772.3657989},
  doi          = {10.1145/3626772.3657989},
  timestamp    = {Sun, 06 Oct 2024 21:14:16 +0200},
  biburl       = {https://dblp.org/rec/conf/sigir/00010P0H00YY24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigir/Liu0Z00ZH0G24,
  author       = {Ziru Liu and
                  Shuchang Liu and
                  Zijian Zhang and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Kesen Zhao and
                  Lantao Hu and
                  Peng Jiang and
                  Kun Gai},
  editor       = {Grace Hui Yang and
                  Hongning Wang and
                  Sam Han and
                  Claudia Hauff and
                  Guido Zuccon and
                  Yi Zhang},
  title        = {Sequential Recommendation for Optimizing Both Immediate Feedback and
                  Long-term Retention},
  booktitle    = {Proceedings of the 47th International {ACM} {SIGIR} Conference on
                  Research and Development in Information Retrieval, {SIGIR} 2024, Washington
                  DC, USA, July 14-18, 2024},
  pages        = {1872--1882},
  publisher    = {{ACM}},
  year         = {2024},
  url          = {https://doi.org/10.1145/3626772.3657829},
  doi          = {10.1145/3626772.3657829},
  timestamp    = {Tue, 23 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sigir/Liu0Z00ZH0G24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigir/Zhang0Y00ZLLZH024,
  author       = {Zijian Zhang and
                  Shuchang Liu and
                  Jiaao Yu and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Chunxu Zhang and
                  Ziru Liu and
                  Qidong Liu and
                  Hongwei Zhao and
                  Lantao Hu and
                  Peng Jiang and
                  Kun Gai},
  editor       = {Grace Hui Yang and
                  Hongning Wang and
                  Sam Han and
                  Claudia Hauff and
                  Guido Zuccon and
                  Yi Zhang},
  title        = {M\({}^{\mbox{3}}\)oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation
                  Framework},
  booktitle    = {Proceedings of the 47th International {ACM} {SIGIR} Conference on
                  Research and Development in Information Retrieval, {SIGIR} 2024, Washington
                  DC, USA, July 14-18, 2024},
  pages        = {893--902},
  publisher    = {{ACM}},
  year         = {2024},
  url          = {https://doi.org/10.1145/3626772.3657686},
  doi          = {10.1145/3626772.3657686},
  timestamp    = {Sun, 21 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/sigir/Zhang0Y00ZLLZH024.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-16108,
  author       = {Xiaobei Wang and
                  Shuchang Liu and
                  Xueliang Wang and
                  Qingpeng Cai and
                  Lantao Hu and
                  Han Li and
                  Peng Jiang and
                  Guangming Xie},
  title        = {Future Impact Decomposition in Request-level Recommendations},
  journal      = {CoRR},
  volume       = {abs/2401.16108},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2401.16108},
  doi          = {10.48550/ARXIV.2401.16108},
  eprinttype    = {arXiv},
  eprint       = {2401.16108},
  timestamp    = {Tue, 06 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2401-16108.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2404-03637,
  author       = {Ziru Liu and
                  Shuchang Liu and
                  Zijian Zhang and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Kesen Zhao and
                  Lantao Hu and
                  Peng Jiang and
                  Kun Gai},
  title        = {Sequential Recommendation for Optimizing Both Immediate Feedback and
                  Long-term Retention},
  journal      = {CoRR},
  volume       = {abs/2404.03637},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2404.03637},
  doi          = {10.48550/ARXIV.2404.03637},
  eprinttype    = {arXiv},
  eprint       = {2404.03637},
  timestamp    = {Tue, 16 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2404-03637.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2404-18465,
  author       = {Zijian Zhang and
                  Shuchang Liu and
                  Jiaao Yu and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Chunxu Zhang and
                  Ziru Liu and
                  Qidong Liu and
                  Hongwei Zhao and
                  Lantao Hu and
                  Peng Jiang and
                  Kun Gai},
  title        = {M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework},
  journal      = {CoRR},
  volume       = {abs/2404.18465},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2404.18465},
  doi          = {10.48550/ARXIV.2404.18465},
  eprinttype    = {arXiv},
  eprint       = {2404.18465},
  timestamp    = {Tue, 04 Jun 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2404-18465.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-01901,
  author       = {Chunhui Li and
                  Cheng{-}Hao Liu and
                  Dianbo Liu and
                  Qingpeng Cai and
                  Ling Pan},
  title        = {Bifurcated Generative Flow Networks},
  journal      = {CoRR},
  volume       = {abs/2406.01901},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.01901},
  doi          = {10.48550/ARXIV.2406.01901},
  eprinttype    = {arXiv},
  eprint       = {2406.01901},
  timestamp    = {Thu, 04 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-01901.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-02213,
  author       = {Haoran He and
                  Emmanuel Bengio and
                  Qingpeng Cai and
                  Ling Pan},
  title        = {Rectifying Reinforcement Learning for Reward Matching},
  journal      = {CoRR},
  volume       = {abs/2406.02213},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.02213},
  doi          = {10.48550/ARXIV.2406.02213},
  eprinttype    = {arXiv},
  eprint       = {2406.02213},
  timestamp    = {Fri, 05 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-02213.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-06043,
  author       = {Ziru Liu and
                  Shuchang Liu and
                  Bin Yang and
                  Zhenghai Xue and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Zijian Zhang and
                  Lantao Hu and
                  Han Li and
                  Peng Jiang},
  title        = {Modeling User Retention through Generative Flow Networks},
  journal      = {CoRR},
  volume       = {abs/2406.06043},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.06043},
  doi          = {10.48550/ARXIV.2406.06043},
  eprinttype    = {arXiv},
  eprint       = {2406.06043},
  timestamp    = {Mon, 22 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-06043.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-14015,
  author       = {Qingpeng Cai and
                  Kaiping Zheng and
                  H. V. Jagadish and
                  Beng Chin Ooi and
                  James Wei Luen Yip},
  title        = {CohortNet: Empowering Cohort Discovery for Interpretable Healthcare
                  Analytics},
  journal      = {CoRR},
  volume       = {abs/2406.14015},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.14015},
  doi          = {10.48550/ARXIV.2406.14015},
  eprinttype    = {arXiv},
  eprint       = {2406.14015},
  timestamp    = {Mon, 15 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-14015.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2408-12470,
  author       = {Jiaju Chen and
                  Chongming Gao and
                  Shuai Yuan and
                  Shuchang Liu and
                  Qingpeng Cai and
                  Peng Jiang},
  title        = {DLCRec: {A} Novel Approach for Managing Diversity in LLM-Based Recommender
                  Systems},
  journal      = {CoRR},
  volume       = {abs/2408.12470},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2408.12470},
  doi          = {10.48550/ARXIV.2408.12470},
  eprinttype    = {arXiv},
  eprint       = {2408.12470},
  timestamp    = {Mon, 30 Sep 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2408-12470.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tkde/CaiCXWXZ23,
  author       = {Qingpeng Cai and
                  Can Cui and
                  Yiyuan Xiong and
                  Wei Wang and
                  Zhongle Xie and
                  Meihui Zhang},
  title        = {A Survey on Deep Reinforcement Learning for Data Processing and Analytics},
  journal      = {{IEEE} Trans. Knowl. Data Eng.},
  volume       = {35},
  number       = {5},
  pages        = {4446--4465},
  year         = {2023},
  url          = {https://doi.org/10.1109/TKDE.2022.3155196},
  doi          = {10.1109/TKDE.2022.3155196},
  timestamp    = {Thu, 27 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tkde/CaiCXWXZ23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/Xue0ZZ0G023,
  author       = {Wanqi Xue and
                  Qingpeng Cai and
                  Ruohan Zhan and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai and
                  Bo An},
  title        = {ResAct: Reinforcing Long-term Engagement in Sequential Recommendation
                  with Residual Actor},
  booktitle    = {The Eleventh International Conference on Learning Representations,
                  {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
  publisher    = {OpenReview.net},
  year         = {2023},
  url          = {https://openreview.net/forum?id=HmPOzJQhbwg},
  timestamp    = {Wed, 24 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/Xue0ZZ0G023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/00060HSMZ0G23,
  author       = {Shuchang Liu and
                  Qingpeng Cai and
                  Zhankui He and
                  Bowen Sun and
                  Julian J. McAuley and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  editor       = {Ambuj K. Singh and
                  Yizhou Sun and
                  Leman Akoglu and
                  Dimitrios Gunopulos and
                  Xifeng Yan and
                  Ravi Kumar and
                  Fatma Ozcan and
                  Jieping Ye},
  title        = {Generative Flow Network for Listwise Recommendation},
  booktitle    = {Proceedings of the 29th {ACM} {SIGKDD} Conference on Knowledge Discovery
                  and Data Mining, {KDD} 2023, Long Beach, CA, USA, August 6-10, 2023},
  pages        = {1524--1534},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3580305.3599364},
  doi          = {10.1145/3580305.3599364},
  timestamp    = {Mon, 25 Sep 2023 08:29:22 +0200},
  biburl       = {https://dblp.org/rec/conf/kdd/00060HSMZ0G23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/Xue0XS0ZJG023,
  author       = {Wanqi Xue and
                  Qingpeng Cai and
                  Zhenghai Xue and
                  Shuo Sun and
                  Shuchang Liu and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai and
                  Bo An},
  editor       = {Ambuj K. Singh and
                  Yizhou Sun and
                  Leman Akoglu and
                  Dimitrios Gunopulos and
                  Xifeng Yan and
                  Ravi Kumar and
                  Fatma Ozcan and
                  Jieping Ye},
  title        = {PrefRec: Recommender Systems with Human Preferences for Reinforcing
                  Long-term User Engagement},
  booktitle    = {Proceedings of the 29th {ACM} {SIGKDD} Conference on Knowledge Discovery
                  and Data Mining, {KDD} 2023, Long Beach, CA, USA, August 6-10, 2023},
  pages        = {2874--2884},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3580305.3599473},
  doi          = {10.1145/3580305.3599473},
  timestamp    = {Fri, 18 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/kdd/Xue0XS0ZJG023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Xue00Z0G023,
  author       = {Zhenghai Xue and
                  Qingpeng Cai and
                  Shuchang Liu and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai and
                  Bo An},
  editor       = {Alice Oh and
                  Tristan Naumann and
                  Amir Globerson and
                  Kate Saenko and
                  Moritz Hardt and
                  Sergey Levine},
  title        = {State Regularized Policy Optimization on Data with Dynamics Shift},
  booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference
                  on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
                  LA, USA, December 10 - 16, 2023},
  year         = {2023},
  url          = {http://papers.nips.cc/paper\_files/paper/2023/hash/67dd6a41bf9539cffc0fc0165e4d0616-Abstract-Conference.html},
  timestamp    = {Fri, 01 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/Xue00Z0G023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Zhao000LZJG23,
  author       = {Kesen Zhao and
                  Shuchang Liu and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Ziru Liu and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  editor       = {Alice Oh and
                  Tristan Naumann and
                  Amir Globerson and
                  Kate Saenko and
                  Moritz Hardt and
                  Sergey Levine},
  title        = {KuaiSim: {A} Comprehensive Simulator for Recommender Systems},
  booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference
                  on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
                  LA, USA, December 10 - 16, 2023},
  year         = {2023},
  url          = {http://papers.nips.cc/paper\_files/paper/2023/hash/8c7f8f98f9a8f5650922dd4545254f28-Abstract-Datasets\_and\_Benchmarks.html},
  timestamp    = {Tue, 04 Jun 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/nips/Zhao000LZJG23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/00010WZXYZJG23,
  author       = {Qingpeng Cai and
                  Shuchang Liu and
                  Xueliang Wang and
                  Tianyou Zuo and
                  Wentao Xie and
                  Bin Yang and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  editor       = {Ying Ding and
                  Jie Tang and
                  Juan F. Sequeda and
                  Lora Aroyo and
                  Carlos Castillo and
                  Geert{-}Jan Houben},
  title        = {Reinforcing User Retention in a Billion Scale Short Video Recommender
                  System},
  booktitle    = {Companion Proceedings of the {ACM} Web Conference 2023, {WWW} 2023,
                  Austin, TX, USA, 30 April 2023 - 4 May 2023},
  pages        = {421--426},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3543873.3584640},
  doi          = {10.1145/3543873.3584640},
  timestamp    = {Mon, 28 Aug 2023 21:17:11 +0200},
  biburl       = {https://dblp.org/rec/conf/www/00010WZXYZJG23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/0001XZX0ZWZXZJG23,
  author       = {Qingpeng Cai and
                  Zhenghai Xue and
                  Chi Zhang and
                  Wanqi Xue and
                  Shuchang Liu and
                  Ruohan Zhan and
                  Xueliang Wang and
                  Tianyou Zuo and
                  Wentao Xie and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  editor       = {Ying Ding and
                  Jie Tang and
                  Juan F. Sequeda and
                  Lora Aroyo and
                  Carlos Castillo and
                  Geert{-}Jan Houben},
  title        = {Two-Stage Constrained Actor-Critic for Short Video Recommendation},
  booktitle    = {Proceedings of the {ACM} Web Conference 2023, {WWW} 2023, Austin,
                  TX, USA, 30 April 2023 - 4 May 2023},
  pages        = {865--875},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3543507.3583259},
  doi          = {10.1145/3543507.3583259},
  timestamp    = {Mon, 28 Aug 2023 21:17:10 +0200},
  biburl       = {https://dblp.org/rec/conf/www/0001XZX0ZWZXZJG23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/00060SWJZJGZZ23,
  author       = {Shuchang Liu and
                  Qingpeng Cai and
                  Bowen Sun and
                  Yuhao Wang and
                  Ji Jiang and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai and
                  Xiangyu Zhao and
                  Yongfeng Zhang},
  editor       = {Ying Ding and
                  Jie Tang and
                  Juan F. Sequeda and
                  Lora Aroyo and
                  Carlos Castillo and
                  Geert{-}Jan Houben},
  title        = {Exploration and Regularization of the Latent Action Space in Recommendation},
  booktitle    = {Proceedings of the {ACM} Web Conference 2023, {WWW} 2023, Austin,
                  TX, USA, 30 April 2023 - 4 May 2023},
  pages        = {833--844},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3543507.3583244},
  doi          = {10.1145/3543507.3583244},
  timestamp    = {Mon, 11 Nov 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/www/00060SWJZJGZZ23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/LiuT0ZGLCHZJG23,
  author       = {Ziru Liu and
                  Jiejie Tian and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Jingtong Gao and
                  Shuchang Liu and
                  Dayou Chen and
                  Tonghao He and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  editor       = {Ying Ding and
                  Jie Tang and
                  Juan F. Sequeda and
                  Lora Aroyo and
                  Carlos Castillo and
                  Geert{-}Jan Houben},
  title        = {Multi-Task Recommendations with Reinforcement Learning},
  booktitle    = {Proceedings of the {ACM} Web Conference 2023, {WWW} 2023, Austin,
                  TX, USA, 30 April 2023 - 4 May 2023},
  pages        = {1273--1282},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3543507.3583467},
  doi          = {10.1145/3543507.3583467},
  timestamp    = {Tue, 30 Jan 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/www/LiuT0ZGLCHZJG23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-01680,
  author       = {Qingpeng Cai and
                  Zhenghai Xue and
                  Chi Zhang and
                  Wanqi Xue and
                  Shuchang Liu and
                  Ruohan Zhan and
                  Xueliang Wang and
                  Tianyou Zuo and
                  Wentao Xie and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  title        = {Two-Stage Constrained Actor-Critic for Short Video Recommendation},
  journal      = {CoRR},
  volume       = {abs/2302.01680},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2302.01680},
  doi          = {10.48550/ARXIV.2302.01680},
  eprinttype    = {arXiv},
  eprint       = {2302.01680},
  timestamp    = {Thu, 29 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2302-01680.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-01724,
  author       = {Qingpeng Cai and
                  Shuchang Liu and
                  Xueliang Wang and
                  Tianyou Zuo and
                  Wentao Xie and
                  Bin Yang and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  title        = {Reinforcing User Retention in a Billion Scale Short Video Recommender
                  System},
  journal      = {CoRR},
  volume       = {abs/2302.01724},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2302.01724},
  doi          = {10.48550/ARXIV.2302.01724},
  eprinttype    = {arXiv},
  eprint       = {2302.01724},
  timestamp    = {Thu, 29 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2302-01724.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-03328,
  author       = {Ziru Liu and
                  Jiejie Tian and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Jingtong Gao and
                  Shuchang Liu and
                  Dayou Chen and
                  Tonghao He and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  title        = {Multi-Task Recommendations with Reinforcement Learning},
  journal      = {CoRR},
  volume       = {abs/2302.03328},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2302.03328},
  doi          = {10.48550/ARXIV.2302.03328},
  eprinttype    = {arXiv},
  eprint       = {2302.03328},
  timestamp    = {Tue, 30 Jan 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2302-03328.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-03431,
  author       = {Shuchang Liu and
                  Qingpeng Cai and
                  Bowen Sun and
                  Yuhao Wang and
                  Ji Jiang and
                  Dong Zheng and
                  Kun Gai and
                  Peng Jiang and
                  Xiangyu Zhao and
                  Yongfeng Zhang},
  title        = {Exploration and Regularization of the Latent Action Space in Recommendation},
  journal      = {CoRR},
  volume       = {abs/2302.03431},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2302.03431},
  doi          = {10.48550/ARXIV.2302.03431},
  eprinttype    = {arXiv},
  eprint       = {2302.03431},
  timestamp    = {Tue, 12 Nov 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2302-03431.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-02239,
  author       = {Shuchang Liu and
                  Qingpeng Cai and
                  Zhankui He and
                  Bowen Sun and
                  Julian J. McAuley and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  title        = {Generative Flow Network for Listwise Recommendation},
  journal      = {CoRR},
  volume       = {abs/2306.02239},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.02239},
  doi          = {10.48550/ARXIV.2306.02239},
  eprinttype    = {arXiv},
  eprint       = {2306.02239},
  timestamp    = {Thu, 29 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-02239.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-03552,
  author       = {Zhenghai Xue and
                  Qingpeng Cai and
                  Shuchang Liu and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai and
                  Bo An},
  title        = {State Regularized Policy Optimization on Data with Dynamics Shift},
  journal      = {CoRR},
  volume       = {abs/2306.03552},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.03552},
  doi          = {10.48550/ARXIV.2306.03552},
  eprinttype    = {arXiv},
  eprint       = {2306.03552},
  timestamp    = {Thu, 29 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-03552.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-06212,
  author       = {Yue Feng and
                  Shuchang Liu and
                  Zhenghai Xue and
                  Qingpeng Cai and
                  Lantao Hu and
                  Peng Jiang and
                  Kun Gai and
                  Fei Sun},
  title        = {A Large Language Model Enhanced Conversational Recommender System},
  journal      = {CoRR},
  volume       = {abs/2308.06212},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2308.06212},
  doi          = {10.48550/ARXIV.2308.06212},
  eprinttype    = {arXiv},
  eprint       = {2308.06212},
  timestamp    = {Sun, 04 Aug 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2308-06212.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-12645,
  author       = {Kesen Zhao and
                  Shuchang Liu and
                  Qingpeng Cai and
                  Xiangyu Zhao and
                  Ziru Liu and
                  Dong Zheng and
                  Peng Jiang and
                  Kun Gai},
  title        = {KuaiSim: {A} Comprehensive Simulator for Recommender Systems},
  journal      = {CoRR},
  volume       = {abs/2309.12645},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2309.12645},
  doi          = {10.48550/ARXIV.2309.12645},
  eprinttype    = {arXiv},
  eprint       = {2309.12645},
  timestamp    = {Tue, 30 Jan 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-12645.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-03984,
  author       = {Zhenghai Xue and
                  Qingpeng Cai and
                  Tianyou Zuo and
                  Bin Yang and
                  Lantao Hu and
                  Peng Jiang and
                  Kun Gai and
                  Bo An},
  title        = {AdaRec: Adaptive Sequential Recommendation for Reinforcing Long-term
                  User Engagement},
  journal      = {CoRR},
  volume       = {abs/2310.03984},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2310.03984},
  doi          = {10.48550/ARXIV.2310.03984},
  eprinttype    = {arXiv},
  eprint       = {2310.03984},
  timestamp    = {Fri, 20 Oct 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2310-03984.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZhangS0ZC00Z22,
  author       = {Wenqiao Zhang and
                  Haochen Shi and
                  Jiannan Guo and
                  Shengyu Zhang and
                  Qingpeng Cai and
                  Juncheng Li and
                  Sihui Luo and
                  Yueting Zhuang},
  title        = {{MAGIC:} Multimodal relAtional Graph adversarIal inferenCe for Diverse
                  and Unpaired Text-Based Image Captioning},
  booktitle    = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
                  2022, Thirty-Fourth Conference on Innovative Applications of Artificial
                  Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
                  in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
                  - March 1, 2022},
  pages        = {3335--3343},
  publisher    = {{AAAI} Press},
  year         = {2022},
  url          = {https://doi.org/10.1609/aaai.v36i3.20243},
  doi          = {10.1609/AAAI.V36I3.20243},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/aaai/ZhangS0ZC00Z22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/ZhangZHZMCO22,
  author       = {Wenqiao Zhang and
                  Lei Zhu and
                  James Hallinan and
                  Shengyu Zhang and
                  Andrew Makmur and
                  Qingpeng Cai and
                  Beng Chin Ooi},
  title        = {BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive
                  Pseudo Labeling and Informative Active Annotation},
  booktitle    = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
                  {CVPR} 2022, New Orleans, LA, USA, June 18-24, 2022},
  pages        = {20634--20644},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/CVPR52688.2022.02001},
  doi          = {10.1109/CVPR52688.2022.02001},
  timestamp    = {Wed, 10 Apr 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/cvpr/ZhangZHZMCO22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icde/CaiZOWY22,
  author       = {Qingpeng Cai and
                  Kaiping Zheng and
                  Beng Chin Ooi and
                  Wei Wang and
                  Chang Yao},
  title        = {{ELDA:} Learning Explicit Dual-Interactions for Healthcare Analytics},
  booktitle    = {38th {IEEE} International Conference on Data Engineering, {ICDE} 2022,
                  Kuala Lumpur, Malaysia, May 9-12, 2022},
  pages        = {393--406},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/ICDE53745.2022.00034},
  doi          = {10.1109/ICDE53745.2022.00034},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icde/CaiZOWY22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-02533,
  author       = {Wenqiao Zhang and
                  Lei Zhu and
                  James Hallinan and
                  Andrew Makmur and
                  Shengyu Zhang and
                  Qingpeng Cai and
                  Beng Chin Ooi},
  title        = {BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive
                  Pseudo Labeling and Informative Active Annotation},
  journal      = {CoRR},
  volume       = {abs/2203.02533},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2203.02533},
  doi          = {10.48550/ARXIV.2203.02533},
  eprinttype    = {arXiv},
  eprint       = {2203.02533},
  timestamp    = {Wed, 10 Apr 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2203-02533.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-13248,
  author       = {Qingpeng Cai and
                  Ruohan Zhan and
                  Chi Zhang and
                  Jie Zheng and
                  Guangwei Ding and
                  Pinghua Gong and
                  Dong Zheng and
                  Peng Jiang},
  title        = {Constrained Reinforcement Learning for Short Video Recommendation},
  journal      = {CoRR},
  volume       = {abs/2205.13248},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2205.13248},
  doi          = {10.48550/ARXIV.2205.13248},
  eprinttype    = {arXiv},
  eprint       = {2205.13248},
  timestamp    = {Thu, 29 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2205-13248.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-02620,
  author       = {Wanqi Xue and
                  Qingpeng Cai and
                  Ruohan Zhan and
                  Dong Zheng and
                  Peng Jiang and
                  Bo An},
  title        = {ResAct: Reinforcing Long-term Engagement in Sequential Recommendation
                  with Residual Actor},
  journal      = {CoRR},
  volume       = {abs/2206.02620},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2206.02620},
  doi          = {10.48550/ARXIV.2206.02620},
  eprinttype    = {arXiv},
  eprint       = {2206.02620},
  timestamp    = {Thu, 29 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2206-02620.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-02779,
  author       = {Wanqi Xue and
                  Qingpeng Cai and
                  Zhenghai Xue and
                  Shuo Sun and
                  Shuchang Liu and
                  Dong Zheng and
                  Peng Jiang and
                  Bo An},
  title        = {PrefRec: Preference-based Recommender Systems for Reinforcing Long-term
                  User Engagement},
  journal      = {CoRR},
  volume       = {abs/2212.02779},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2212.02779},
  doi          = {10.48550/ARXIV.2212.02779},
  eprinttype    = {arXiv},
  eprint       = {2212.02779},
  timestamp    = {Thu, 29 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-02779.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aamas/PanCH21,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Longbo Huang},
  title        = {Exploration in policy optimization through multiple paths},
  journal      = {Auton. Agents Multi Agent Syst.},
  volume       = {35},
  number       = {2},
  pages        = {33},
  year         = {2021},
  url          = {https://doi.org/10.1007/s10458-021-09518-6},
  doi          = {10.1007/S10458-021-09518-6},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/aamas/PanCH21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-04526,
  author       = {Qingpeng Cai and
                  Can Cui and
                  Yiyuan Xiong and
                  Wei Wang and
                  Zhongle Xie and
                  Meihui Zhang},
  title        = {A Survey on Deep Reinforcement Learning for Data Processing and Analytics},
  journal      = {CoRR},
  volume       = {abs/2108.04526},
  year         = {2021},
  url          = {https://arxiv.org/abs/2108.04526},
  eprinttype    = {arXiv},
  eprint       = {2108.04526},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2108-04526.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-06558,
  author       = {Wenqiao Zhang and
                  Haochen Shi and
                  Jiannan Guo and
                  Shengyu Zhang and
                  Qingpeng Cai and
                  Juncheng Li and
                  Sihui Luo and
                  Yueting Zhuang},
  title        = {{MAGIC:} Multimodal relAtional Graph adversarIal inferenCe for Diverse
                  and Unpaired Text-based Image Captioning},
  journal      = {CoRR},
  volume       = {abs/2112.06558},
  year         = {2021},
  url          = {https://arxiv.org/abs/2112.06558},
  eprinttype    = {arXiv},
  eprint       = {2112.06558},
  timestamp    = {Thu, 01 Dec 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2112-06558.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/CaiPT20,
  author       = {Qingpeng Cai and
                  Ling Pan and
                  Pingzhong Tang},
  title        = {Deterministic Value-Policy Gradients},
  booktitle    = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
                  2020, The Thirty-Second Innovative Applications of Artificial Intelligence
                  Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
                  Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
                  February 7-12, 2020},
  pages        = {3316--3323},
  publisher    = {{AAAI} Press},
  year         = {2020},
  url          = {https://doi.org/10.1609/aaai.v34i04.5732},
  doi          = {10.1609/AAAI.V34I04.5732},
  timestamp    = {Sat, 21 Oct 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/aaai/CaiPT20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/PanCH20,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Longbo Huang},
  editor       = {Amal El Fallah Seghrouchni and
                  Gita Sukthankar and
                  Bo An and
                  Neil Yorke{-}Smith},
  title        = {Multi-Path Policy Optimization},
  booktitle    = {Proceedings of the 19th International Conference on Autonomous Agents
                  and Multiagent Systems, {AAMAS} '20, Auckland, New Zealand, May 9-13,
                  2020},
  pages        = {1001--1009},
  publisher    = {International Foundation for Autonomous Agents and Multiagent Systems},
  year         = {2020},
  url          = {https://dl.acm.org/doi/10.5555/3398761.3398878},
  doi          = {10.5555/3398761.3398878},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/atal/PanCH20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/PanCM0H20,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Qi Meng and
                  Wei Chen and
                  Longbo Huang},
  editor       = {Christian Bessiere},
  title        = {Reinforcement Learning with Dynamic Boltzmann Softmax Updates},
  booktitle    = {Proceedings of the Twenty-Ninth International Joint Conference on
                  Artificial Intelligence, {IJCAI} 2020},
  pages        = {1992--1998},
  publisher    = {ijcai.org},
  year         = {2020},
  url          = {https://doi.org/10.24963/ijcai.2020/276},
  doi          = {10.24963/IJCAI.2020/276},
  timestamp    = {Tue, 15 Oct 2024 16:43:28 +0200},
  biburl       = {https://dblp.org/rec/conf/ijcai/PanCM0H20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/PanCH20,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Longbo Huang},
  editor       = {Hugo Larochelle and
                  Marc'Aurelio Ranzato and
                  Raia Hadsell and
                  Maria{-}Florina Balcan and
                  Hsuan{-}Tien Lin},
  title        = {Softmax Deep Double Deterministic Policy Gradients},
  booktitle    = {Advances in Neural Information Processing Systems 33: Annual Conference
                  on Neural Information Processing Systems 2020, NeurIPS 2020, December
                  6-12, 2020, virtual},
  year         = {2020},
  url          = {https://proceedings.neurips.cc/paper/2020/hash/884d247c6f65a96a7da4d1105d584ddd-Abstract.html},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/PanCH20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-12206,
  author       = {Jianxiong Wei and
                  Anxiang Zeng and
                  Yueqiu Wu and
                  Peng Guo and
                  Qingsong Hua and
                  Qingpeng Cai},
  title        = {Generator and Critic: {A} Deep Reinforcement Learning Approach for
                  Slate Re-ranking in E-commerce},
  journal      = {CoRR},
  volume       = {abs/2005.12206},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.12206},
  eprinttype    = {arXiv},
  eprint       = {2005.12206},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-12206.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-09177,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Longbo Huang},
  title        = {Softmax Deep Double Deterministic Policy Gradients},
  journal      = {CoRR},
  volume       = {abs/2010.09177},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.09177},
  eprinttype    = {arXiv},
  eprint       = {2010.09177},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-09177.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/PanCFTH19,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Zhixuan Fang and
                  Pingzhong Tang and
                  Longbo Huang},
  title        = {A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike
                  Sharing Systems},
  booktitle    = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
                  2019, The Thirty-First Innovative Applications of Artificial Intelligence
                  Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
                  Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
                  USA, January 27 - February 1, 2019},
  pages        = {1393--1400},
  publisher    = {{AAAI} Press},
  year         = {2019},
  url          = {https://doi.org/10.1609/aaai.v33i01.33011393},
  doi          = {10.1609/AAAI.V33I01.33011393},
  timestamp    = {Mon, 04 Sep 2023 12:29:24 +0200},
  biburl       = {https://dblp.org/rec/conf/aaai/PanCFTH19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/PanCZPDHHT19,
  author       = {Feiyang Pan and
                  Qingpeng Cai and
                  Anxiang Zeng and
                  Chun{-}Xiang Pan and
                  Qing Da and
                  Hua{-}Lin He and
                  Qing He and
                  Pingzhong Tang},
  title        = {Policy Optimization with Model-Based Explorations},
  booktitle    = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
                  2019, The Thirty-First Innovative Applications of Artificial Intelligence
                  Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
                  Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
                  USA, January 27 - February 1, 2019},
  pages        = {4675--4682},
  publisher    = {{AAAI} Press},
  year         = {2019},
  url          = {https://doi.org/10.1609/aaai.v33i01.33014675},
  doi          = {10.1609/AAAI.V33I01.33014675},
  timestamp    = {Sun, 20 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/aaai/PanCZPDHHT19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/PanCTZH19,
  author       = {Feiyang Pan and
                  Qingpeng Cai and
                  Pingzhong Tang and
                  Fuzhen Zhuang and
                  Qing He},
  editor       = {Ling Liu and
                  Ryen W. White and
                  Amin Mantrach and
                  Fabrizio Silvestri and
                  Julian J. McAuley and
                  Ricardo Baeza{-}Yates and
                  Leila Zia},
  title        = {Policy Gradients for Contextual Recommendations},
  booktitle    = {The World Wide Web Conference, {WWW} 2019, San Francisco, CA, USA,
                  May 13-17, 2019},
  pages        = {1421--1431},
  publisher    = {{ACM}},
  year         = {2019},
  url          = {https://doi.org/10.1145/3308558.3313616},
  doi          = {10.1145/3308558.3313616},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/www/PanCTZH19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-05926,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Qi Meng and
                  Wei Chen and
                  Longbo Huang and
                  Tie{-}Yan Liu},
  title        = {Reinforcement Learning with Dynamic Boltzmann Softmax Updates},
  journal      = {CoRR},
  volume       = {abs/1903.05926},
  year         = {2019},
  url          = {http://arxiv.org/abs/1903.05926},
  eprinttype    = {arXiv},
  eprint       = {1903.05926},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1903-05926.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-06639,
  author       = {Qingpeng Cai and
                  Will Hang and
                  Azalia Mirhoseini and
                  George Tucker and
                  Jingtao Wang and
                  Wei Wei},
  title        = {Reinforcement Learning Driven Heuristic Optimization},
  journal      = {CoRR},
  volume       = {abs/1906.06639},
  year         = {2019},
  url          = {http://arxiv.org/abs/1906.06639},
  eprinttype    = {arXiv},
  eprint       = {1906.06639},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1906-06639.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-03939,
  author       = {Qingpeng Cai and
                  Ling Pan and
                  Pingzhong Tang},
  title        = {Deterministic Value-Policy Gradients},
  journal      = {CoRR},
  volume       = {abs/1909.03939},
  year         = {2019},
  url          = {http://arxiv.org/abs/1909.03939},
  eprinttype    = {arXiv},
  eprint       = {1909.03939},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1909-03939.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-04207,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Longbo Huang},
  title        = {Multi-Path Policy Optimization},
  journal      = {CoRR},
  volume       = {abs/1911.04207},
  year         = {2019},
  url          = {http://arxiv.org/abs/1911.04207},
  eprinttype    = {arXiv},
  eprint       = {1911.04207},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1911-04207.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcss/DongLZC18,
  author       = {Rongsheng Dong and
                  Libing Li and
                  Qingpeng Zhang and
                  Guoyong Cai},
  title        = {Information Diffusion on Social Media During Natural Disasters},
  journal      = {{IEEE} Trans. Comput. Soc. Syst.},
  volume       = {5},
  number       = {1},
  pages        = {265--276},
  year         = {2018},
  url          = {https://doi.org/10.1109/TCSS.2017.2786545},
  doi          = {10.1109/TCSS.2017.2786545},
  timestamp    = {Mon, 08 Jun 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tcss/DongLZC18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/CaiFTZ18,
  author       = {Qingpeng Cai and
                  Aris Filos{-}Ratsikas and
                  Pingzhong Tang and
                  Yiwei Zhang},
  editor       = {Sheila A. McIlraith and
                  Kilian Q. Weinberger},
  title        = {Reinforcement Mechanism Design for Fraudulent Behaviour in e-Commerce},
  booktitle    = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence,
                  (AAAI-18), the 30th innovative Applications of Artificial Intelligence
                  (IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in
                  Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February
                  2-7, 2018},
  pages        = {957--964},
  publisher    = {{AAAI} Press},
  year         = {2018},
  url          = {https://doi.org/10.1609/aaai.v32i1.11452},
  doi          = {10.1609/AAAI.V32I1.11452},
  timestamp    = {Sat, 30 Sep 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/aaai/CaiFTZ18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/CaiTZ18,
  author       = {Qingpeng Cai and
                  Pingzhong Tang and
                  Yulong Zeng},
  editor       = {Elisabeth Andr{\'{e}} and
                  Sven Koenig and
                  Mehdi Dastani and
                  Gita Sukthankar},
  title        = {Ranking Mechanism Design for Price-setting Agents in E-commerce},
  booktitle    = {Proceedings of the 17th International Conference on Autonomous Agents
                  and MultiAgent Systems, {AAMAS} 2018, Stockholm, Sweden, July 10-15,
                  2018},
  pages        = {1504--1512},
  publisher    = {International Foundation for Autonomous Agents and Multiagent Systems
                  Richland, SC, {USA} / {ACM}},
  year         = {2018},
  url          = {http://dl.acm.org/citation.cfm?id=3237925},
  timestamp    = {Sat, 30 Sep 2023 09:34:53 +0200},
  biburl       = {https://dblp.org/rec/conf/atal/CaiTZ18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/CaiFTZ18,
  author       = {Qingpeng Cai and
                  Aris Filos{-}Ratsikas and
                  Pingzhong Tang and
                  Yiwei Zhang},
  editor       = {Pierre{-}Antoine Champin and
                  Fabien Gandon and
                  Mounia Lalmas and
                  Panagiotis G. Ipeirotis},
  title        = {Reinforcement Mechanism Design for e-commerce},
  booktitle    = {Proceedings of the 2018 World Wide Web Conference on World Wide Web,
                  {WWW} 2018, Lyon, France, April 23-27, 2018},
  pages        = {1339--1348},
  publisher    = {{ACM}},
  year         = {2018},
  url          = {https://doi.org/10.1145/3178876.3186039},
  doi          = {10.1145/3178876.3186039},
  timestamp    = {Wed, 07 Dec 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/www/CaiFTZ18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-04162,
  author       = {Feiyang Pan and
                  Qingpeng Cai and
                  Pingzhong Tang and
                  Fuzhen Zhuang and
                  Qing He},
  title        = {Policy Gradients for Contextual Bandits},
  journal      = {CoRR},
  volume       = {abs/1802.04162},
  year         = {2018},
  url          = {http://arxiv.org/abs/1802.04162},
  eprinttype    = {arXiv},
  eprint       = {1802.04162},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1802-04162.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-04592,
  author       = {Ling Pan and
                  Qingpeng Cai and
                  Zhixuan Fang and
                  Pingzhong Tang and
                  Longbo Huang},
  title        = {Rebalancing Dockless Bike Sharing Systems},
  journal      = {CoRR},
  volume       = {abs/1802.04592},
  year         = {2018},
  url          = {http://arxiv.org/abs/1802.04592},
  eprinttype    = {arXiv},
  eprint       = {1802.04592},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1802-04592.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1807-03708,
  author       = {Qingpeng Cai and
                  Ling Pan and
                  Pingzhong Tang},
  title        = {Generalized deterministic policy gradient algorithms},
  journal      = {CoRR},
  volume       = {abs/1807.03708},
  year         = {2018},
  url          = {http://arxiv.org/abs/1807.03708},
  eprinttype    = {arXiv},
  eprint       = {1807.03708},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1807-03708.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-07350,
  author       = {Feiyang Pan and
                  Qingpeng Cai and
                  Anxiang Zeng and
                  Chun{-}Xiang Pan and
                  Qing Da and
                  Hua{-}Lin He and
                  Qing He and
                  Pingzhong Tang},
  title        = {Policy Optimization with Model-based Explorations},
  journal      = {CoRR},
  volume       = {abs/1811.07350},
  year         = {2018},
  url          = {http://arxiv.org/abs/1811.07350},
  eprinttype    = {arXiv},
  eprint       = {1811.07350},
  timestamp    = {Sun, 20 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1811-07350.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/LiuCZ17,
  author       = {Chang Liu and
                  Qingpeng Cai and
                  Yukui Zhang},
  editor       = {Kate Larson and
                  Michael Winikoff and
                  Sanmay Das and
                  Edmund H. Durfee},
  title        = {Multi-armed Bandit Mechanism with Private Histories},
  booktitle    = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent
                  Systems, {AAMAS} 2017, S{\~{a}}o Paulo, Brazil, May 8-12, 2017},
  pages        = {1607--1609},
  publisher    = {{ACM}},
  year         = {2017},
  url          = {http://dl.acm.org/citation.cfm?id=3091378},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/atal/LiuCZ17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-07607,
  author       = {Qingpeng Cai and
                  Aris Filos{-}Ratsikas and
                  Pingzhong Tang and
                  Yiwei Zhang},
  title        = {Reinforcement Mechanism Design for e-commerce},
  journal      = {CoRR},
  volume       = {abs/1708.07607},
  year         = {2017},
  url          = {http://arxiv.org/abs/1708.07607},
  eprinttype    = {arXiv},
  eprint       = {1708.07607},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1708-07607.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icnc/LiuCCDY16,
  author       = {Qingpeng Liu and
                  Hua Cai and
                  Guangqiu Chen and
                  Shuang Dou and
                  Yong Yang},
  title        = {An image mosaic method based on improving seam line},
  booktitle    = {12th International Conference on Natural Computation, Fuzzy Systems
                  and Knowledge Discovery, {ICNC-FSKD} 2016, Changsha, China, August
                  13-15, 2016},
  pages        = {414--418},
  publisher    = {{IEEE}},
  year         = {2016},
  url          = {https://doi.org/10.1109/FSKD.2016.7603209},
  doi          = {10.1109/FSKD.2016.7603209},
  timestamp    = {Wed, 16 Oct 2019 14:14:55 +0200},
  biburl       = {https://dblp.org/rec/conf/icnc/LiuCCDY16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/CaiFT16,
  author       = {Qingpeng Cai and
                  Aris Filos{-}Ratsikas and
                  Pingzhong Tang},
  editor       = {Subbarao Kambhampati},
  title        = {Facility Location with Minimax Envy},
  booktitle    = {Proceedings of the Twenty-Fifth International Joint Conference on
                  Artificial Intelligence, {IJCAI} 2016, New York, NY, USA, 9-15 July
                  2016},
  pages        = {137--143},
  publisher    = {{IJCAI/AAAI} Press},
  year         = {2016},
  url          = {http://www.ijcai.org/Abstract/16/027},
  timestamp    = {Fri, 18 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ijcai/CaiFT16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/recsys/CaiFLT16,
  author       = {Qingpeng Cai and
                  Aris Filos{-}Ratsikas and
                  Chang Liu and
                  Pingzhong Tang},
  editor       = {Shilad Sen and
                  Werner Geyer and
                  Jill Freyne and
                  Pablo Castells},
  title        = {Mechanism Design for Personalized Recommender Systems},
  booktitle    = {Proceedings of the 10th {ACM} Conference on Recommender Systems, Boston,
                  MA, USA, September 15-19, 2016},
  pages        = {159--166},
  publisher    = {{ACM}},
  year         = {2016},
  url          = {https://doi.org/10.1145/2959100.2959135},
  doi          = {10.1145/2959100.2959135},
  timestamp    = {Wed, 07 Dec 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/recsys/CaiFLT16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}