{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:10:33Z","timestamp":1767978633235,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8462977","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"7525-7532","source":"Crossref","is-referenced-by-count":20,"title":["Cross-Domain Transfer in Reinforcement Learning Using Target Apprentice"],"prefix":"10.1109","author":[{"given":"Girish","family":"Joshi","sequence":"first","affiliation":[]},{"given":"Girish","family":"Chowdhary","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Unsupervised cross-domain transfer in policy gradient reinforcement learning via manifold alignment","author":"ammar","year":"2015","journal-title":"Proc Of AAAI"},{"key":"ref11","first-page":"672","article-title":"General game learning using knowledge transfer","author":"banerjee","year":"2007","journal-title":"IJCAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref13","first-page":"254","article-title":"Relational macros for transfer in reinforcement learning","author":"torrey","year":"2007","journal-title":"Int Conf Inductive Logic Programming"},{"key":"ref14","first-page":"415","article-title":"Value-function-based transfer for reinforcement learning using structure mapping","volume":"21","author":"liu","year":"1999","journal-title":"Proceedings of the National Conference on Artificial Intelligence"},{"key":"ref15","first-page":"895","volume":"7","year":"2007","journal-title":"IJCAI"},{"key":"ref16","first-page":"3","article-title":"Manifold alignment without correspondence","volume":"2","author":"wang","year":"2009","journal-title":"IJCAI"},{"key":"ref17","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":"ref18","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273607"},{"key":"ref4","author":"rahat","year":"2017"},{"key":"ref3","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","author":"astrom","year":"2013","journal-title":"Adaptive Control"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102352"},{"key":"ref8","first-page":"880","article-title":"Value functions for rl-based behavior transfer: A comparative study","volume":"20","author":"taylor","year":"1999","journal-title":"Proceedings of the National Conference on Artificial Intelligence"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631353"},{"key":"ref2","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":"ref1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","first-page":"383","article-title":"Reinforcement learning transfer via sparse coding","volume":"1","author":"ammar","year":"2012","journal-title":"Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume"},{"key":"ref20","first-page":"2125","article-title":"Transfer learning via inter-task mappings for temporal difference learning","volume":"8","author":"taylor","year":"2007","journal-title":"Lournal of Machine Learning Research"},{"key":"ref22","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","author":"randlov","year":"1998","journal-title":"Proceedings of the Fifteenth International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2012.03.007"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MCS.2005.1499389","article-title":"Bicycle dynamics and control","volume":"25","author":"astrom","year":"2005","journal-title":"IEEE Control Systems Magazine"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08462977.pdf?arnumber=8462977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T03:24:23Z","timestamp":1598239463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8462977","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}