{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:43:55Z","timestamp":1755801835752,"version":"3.44.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/robio49542.2019.8961847","type":"proceedings-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T14:49:51Z","timestamp":1579618191000},"page":"1127-1132","source":"Crossref","is-referenced-by-count":1,"title":["Obstacle Avoidance with Reinforcement Learning and Adaptive Resonance Theory"],"prefix":"10.1109","author":[{"given":"Lingjian","family":"Ye","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China,518055"}]},{"given":"Yimin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China,518055"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Learning by playing-solving sparse reward tasks from scratch","author":"riedmiller","year":"2018","journal-title":"arXiv preprint arXiv 1802 10363"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1062"},{"key":"ref12","article-title":"Hierarchical imitation and reinforcement learning","author":"le","year":"2018","journal-title":"arXiv preprint arXiv 1803 00590"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref15","first-page":"4987","article-title":"Online reinforcement learning in stochastic games","author":"wei","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90056-B"},{"key":"ref17","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref19","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ARGENCON.2018.8646065"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2014.929191"},{"key":"ref6","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795643"},{"key":"ref8","first-page":"689","article-title":"Safe and nested subgame solving for imperfect-information games","author":"brown","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759428"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.06.066"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3321894"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300636"},{"key":"ref21","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":"ref23","article-title":"Simulated car racing championship: Competition software manual","author":"loiacono","year":"2013","journal-title":"arXiv Preprint arXiv 1304 1672"}],"event":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2019,12,6]]},"location":"Dali, China","end":{"date-parts":[[2019,12,8]]}},"container-title":["2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8953068\/8961374\/08961847.pdf?arnumber=8961847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:34:52Z","timestamp":1755714892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8961847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/robio49542.2019.8961847","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}