{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:30:40Z","timestamp":1730266240370,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/ijcnn.2018.8489595","type":"proceedings-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T22:25:09Z","timestamp":1539987909000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Cyber-Human Approach For Learning Human Intention And Shape Robotic Behavior Based On Task Demonstration"],"prefix":"10.1109","author":[{"given":"Vinicius G.","family":"Goecks","sequence":"first","affiliation":[]},{"given":"Gregory M.","family":"Gremillion","sequence":"additional","affiliation":[]},{"given":"Hannah C.","family":"Lehman","sequence":"additional","affiliation":[]},{"given":"William D.","family":"Nothwang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Human Interaction for Effective Reinforcement Learning","author":"le\u00f3n","year":"0","journal-title":"Ke Tu-Darmstadt De"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICRA.2013.6630809"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1016\/j.asoc.2014.01.013"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1016\/j.ins.2017.04.025"},{"key":"ref14","first-page":"116","article-title":"Ideal gas optimization algorithm","volume":"15","author":"shams","year":"2017","journal-title":"International Journal of Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1016\/j.eswa.2013.05.053"},{"key":"ref16","volume":"15","author":"ross","year":"2010","journal-title":"A reduction of imitation learning and structured prediction to no-regret online learning"},{"key":"ref17","first-page":"4565","article-title":"Generative Adversarial Imitation Learning","author":"ho","year":"2016","journal-title":"NIPS"},{"key":"ref18","article-title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","volume":"48","author":"finn","year":"2016","journal-title":"ICML 2016"},{"key":"ref19","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"year":"2016","author":"rahmatizadeh","journal-title":"Learning real manipulation tasks from virtual demonstrations using lstm","key":"ref4"},{"key":"ref3","article-title":"Deep TAMER: interactive agent shaping in high-dimensional state spaces","volume":"abs 1709 10163","author":"warnell","year":"2017","journal-title":"CoRR"},{"key":"ref6","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"ArXiv"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICRA.2017.7989247"},{"key":"ref8","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","volume":"6","author":"thomaz","year":"2006","journal-title":"AAAI"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TPAMI.2013.218"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/j.artint.2015.03.009"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ROMAN.2006.314459"},{"year":"2012","author":"knox","journal-title":"Learning from Human-Generated Reward Learning from Human-Generated Reward","key":"ref1"},{"key":"ref20","first-page":"387","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML-14)"},{"key":"ref22","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":"ref21","first-page":"1","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013","journal-title":"Arxiv preprint arXiv"},{"key":"ref24","first-page":"1","article-title":"Adam: a Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"Proceedings of the 2015 International Conference on Learning Representations"},{"year":"1992","author":"lin","journal-title":"Reinforcement learning for robots using neural networks","key":"ref23"},{"year":"2017","author":"shah","journal-title":"AirSim High-Fidelity Visual and Physical","key":"ref25"}],"event":{"name":"2018 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2018,7,8]]},"location":"Rio de Janeiro","end":{"date-parts":[[2018,7,13]]}},"container-title":["2018 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8465565\/8488986\/08489595.pdf?arnumber=8489595","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:56:26Z","timestamp":1598234186000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8489595\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2018.8489595","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}