{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T15:29:38Z","timestamp":1751038178328,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,8,23]],"date-time":"2017-08-23T00:00:00Z","timestamp":1503446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,8,23]]},"DOI":"10.1145\/3106426.3109426","type":"proceedings-article","created":{"date-parts":[[2017,8,10]],"date-time":"2017-08-10T12:12:36Z","timestamp":1502367156000},"page":"963-966","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep deformable Q-Network"],"prefix":"10.1145","author":[{"given":"Beibei","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangsheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawar","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,8,23]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mnih Volodymyr Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. \"Playing atari with deep reinforcement learning.\" arXiv preprint arXiv:1312.5602 (2013).  Mnih Volodymyr Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. \"Playing atari with deep reinforcement learning.\" arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_3_1","unstructured":"Hausknecht M. and Stone P. 2015. Deep recurrent q-learning for partially observable mdps. arXiv preprint arXiv:1507.06527.  Hausknecht M. and Stone P. 2015. Deep recurrent q-learning for partially observable mdps. arXiv preprint arXiv:1507.06527."},{"key":"e_1_3_2_1_4_1","unstructured":"Osband I. Blundell C. Pritzel A. and Van Roy B. 2016. Deep exploration via bootstrapped DQN. In Advances In Neural Information Processing Systems (pp. 4026--4034).  Osband I. Blundell C. Pritzel A. and Van Roy B. 2016. Deep exploration via bootstrapped DQN. In Advances In Neural Information Processing Systems (pp. 4026--4034)."},{"key":"e_1_3_2_1_5_1","unstructured":"Sutton R.S. and Barto A.G. 1998. Reinforcement learning: An introduction (Vol. 1 No. 1). Cambridge: MIT press.   Sutton R.S. and Barto A.G. 1998. Reinforcement learning: An introduction (Vol. 1 No. 1). Cambridge: MIT press."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Van Hasselt H. Guez A. and Silver D. 2016 March. Deep Reinforcement Learning with Double Q-Learning. In AAAI (pp. 2094--2100).   Van Hasselt H. Guez A. and Silver D. 2016 March. Deep Reinforcement Learning with Double Q-Learning. In AAAI (pp. 2094--2100).","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_1_7_1","unstructured":"Wang Z. Schaul T. Hessel M. van Hasselt H. Lanctot M. and de Freitas N. 2015. Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581.  Wang Z. Schaul T. Hessel M. van Hasselt H. Lanctot M. and de Freitas N. 2015. Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581."},{"key":"e_1_3_2_1_8_1","unstructured":"Schulman J. Moritz P. Levine S. Jordan M. and Abbeel P. 2015. High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438.  Schulman J. Moritz P. Levine S. Jordan M. and Abbeel P. 2015. High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Dai J. Qi H. Xiong Y. Li Y. Zhang G. Hu H. and Wei Y. 2017. Deformable Convolutional Networks. arXiv preprint arXiv:1703.06211.  Dai J. Qi H. Xiong Y. Li Y. Zhang G. Hu H. and Wei Y. 2017. Deformable Convolutional Networks. arXiv preprint arXiv:1703.06211.","DOI":"10.1109\/ICCV.2017.89"},{"volume-title":"Active Convolution: Learning the Shape of Convolution for Image Classification. arXiv preprint arXiv:1703.09076.","year":"2017","author":"Jeon Y.","key":"e_1_3_2_1_10_1"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2818--2826)","author":"Szegedy C.","key":"e_1_3_2_1_11_1"},{"key":"e_1_3_2_1_12_1","unstructured":"Simonyan K. and Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.  Simonyan K. and Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"e_1_3_2_1_13_1","unstructured":"Krizhevsky A. Sutskever I. and Hinton G.E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097--1105).   Krizhevsky A. Sutskever I. and Hinton G.E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097--1105)."},{"key":"e_1_3_2_1_14_1","unstructured":"Wang J. Zhou J. Wonka P. and Ye J. 2013. Advances in neural information processing systems. In Neural information processing systems foundation.  Wang J. Zhou J. Wonka P. and Ye J. 2013. Advances in neural information processing systems. In Neural information processing systems foundation."},{"volume-title":"Cambridge: MIT Press.","year":"1998","author":"Sutton R.S.","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","unstructured":"Stadie B.C. Levine S. and Abbeel P. 2015. Incentivizing exploration in reinforcement learning with deep predictive models. arXiv preprint arXiv:1507.00814.  Stadie B.C. Levine S. and Abbeel P. 2015. Incentivizing exploration in reinforcement learning with deep predictive models. arXiv preprint arXiv:1507.00814."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_1_18_1","unstructured":"Sutton R.S. and Barto A.G. 1998. Reinforcement learning: An introduction (Vol. 1 No. 1). Cambridge: MIT press.   Sutton R.S. and Barto A.G. 1998. Reinforcement learning: An introduction (Vol. 1 No. 1). Cambridge: MIT press."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_20_1","unstructured":"Rummery G.A. and Niranjan M. 1994. On-line Q-learning using connectionist systems. University of Cambridge Department of Engineering.  Rummery G.A. and Niranjan M. 1994. On-line Q-learning using connectionist systems. University of Cambridge Department of Engineering."},{"first-page":"1057","volume-title":"NIPS (Vol. 99","author":"Sutton R.S.","key":"e_1_3_2_1_21_1"},{"key":"e_1_3_2_1_22_1","unstructured":"Krizhevsky A. Sutskever I. and Hinton G.E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097--1105).   Krizhevsky A. Sutskever I. and Hinton G.E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097--1105)."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3431--3440)","author":"Long J.","key":"e_1_3_2_1_23_1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"volume-title":"International Conference on Machine Learning (pp. 1928--1937)","author":"Mnih V.","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","unstructured":"Sorokin I. Seleznev A. Pavlov M. Fedorov A. and Ignateva A. 2015. Deep attention recurrent Q-network. arXiv preprint arXiv:1512.01693.  Sorokin I. Seleznev A. Pavlov M. Fedorov A. and Ignateva A. 2015. Deep attention recurrent Q-network. arXiv preprint arXiv:1512.01693."},{"key":"e_1_3_2_1_27_1","unstructured":"Schaul T. Quan J. Antonoglou I. and Silver D. 2015. Prioritized experience replay. arXiv preprint arXiv:1511.05952.  Schaul T. Quan J. Antonoglou I. and Silver D. 2015. Prioritized experience replay. arXiv preprint arXiv:1511.05952."}],"event":{"name":"WI '17: International Conference on Web Intelligence 2017","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","TCII IEEE Computer Society Technical Committee on Intelligent Informatics","Web Intelligence Consortium"],"location":"Leipzig Germany","acronym":"WI '17"},"container-title":["Proceedings of the International Conference on Web Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3106426.3109426","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3106426.3109426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:30:09Z","timestamp":1750217409000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3106426.3109426"}},"subtitle":["an extension of deep Q-Network"],"short-title":[],"issued":{"date-parts":[[2017,8,23]]},"references-count":27,"alternative-id":["10.1145\/3106426.3109426","10.1145\/3106426"],"URL":"https:\/\/doi.org\/10.1145\/3106426.3109426","relation":{},"subject":[],"published":{"date-parts":[[2017,8,23]]},"assertion":[{"value":"2017-08-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}