{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:57:29Z","timestamp":1760597849801,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/icpr.2018.8546182","type":"proceedings-article","created":{"date-parts":[[2018,11,29]],"date-time":"2018-11-29T19:17:38Z","timestamp":1543519058000},"page":"67-72","source":"Crossref","is-referenced-by-count":9,"title":["Learning Evasion Strategy in Pursuit-Evasion by Deep Q-network"],"prefix":"10.1109","author":[{"given":"Jiagang","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref11","article-title":"Lecture 6. 5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"journal-title":"Massively parallel methods for deep reinforcement learning","year":"2015","author":"nair","key":"ref12"},{"key":"ref13","first-page":"2579","article-title":"Visualizing high-dimensional data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Multi-Agent Deep Reinforcement Learning","year":"2016","author":"egorov","key":"ref14"},{"key":"ref15","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"journal-title":"Giraffe Using deep reinforcement learning to play chess","year":"2015","author":"lai","key":"ref16"},{"journal-title":"Prioritized experience replay","year":"2015","author":"schaul","key":"ref17"},{"journal-title":"Towards vision-based deep reinforcement learning for robotic motion control","year":"2015","author":"zhang","key":"ref18"},{"journal-title":"Action-conditional video prediction using deep networks in atari games","year":"2015","author":"oh","key":"ref19"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377314"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0317-9"},{"key":"ref3","first-page":"455","article-title":"Formation control of underactuated marine vehicles with communication constraints","volume":"50","author":"even","year":"2006","journal-title":"Control of Marine"},{"key":"ref6","first-page":"143","article-title":"Muti-Robot control system for pursuit-evasion problem","volume":"60","author":"daniel","year":"2009","journal-title":"Journal of Electrical Engineering"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2007.4433724"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s10514-011-9241-4","article-title":"Search and pursuit-evasion in mobile robotics","volume":"31","author":"timothy","year":"2011","journal-title":"Autonomous Robots"},{"key":"ref2","first-page":"3962","article-title":"A time-optimal control strategy for pursuit-evasion games problems","volume":"4","author":"hin","year":"2004","journal-title":"2004 IEEE International Conference on Robotics and Automation"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980467"},{"journal-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"mnih","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ-IEEE.2016.7737744"},{"journal-title":"Deep reinforcement learning with double q-learning","year":"2015","author":"van hasselt","key":"ref21"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","article-title":"Cooperative Multi-agent Control Using Deep Reinforcement Learning","author":"gupta","year":"2017","journal-title":"Autonomous Agents and Multiagent Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SYSCON.2016.7490542"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0315-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-009-9102-0"}],"event":{"name":"2018 24th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2018,8,20]]},"location":"Beijing","end":{"date-parts":[[2018,8,24]]}},"container-title":["2018 24th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8527858\/8545020\/08546182.pdf?arnumber=8546182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T09:18:59Z","timestamp":1643275139000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8546182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icpr.2018.8546182","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}