{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T14:40:39Z","timestamp":1688913639340},"reference-count":13,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,1,9]],"date-time":"2014-01-09T00:00:00Z","timestamp":1389225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["K\u00fcnstl Intell"],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1007\/s13218-013-0286-8","type":"journal-article","created":{"date-parts":[[2014,1,8]],"date-time":"2014-01-08T07:25:09Z","timestamp":1389165909000},"page":"7-14","source":"Crossref","is-referenced-by-count":3,"title":["Automated Transfer for Reinforcement Learning Tasks"],"prefix":"10.1007","volume":"28","author":[{"given":"Haitham","family":"Bou Ammar","sequence":"first","affiliation":[]},{"given":"Siqi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Karl","family":"Tuyls","sequence":"additional","affiliation":[]},{"given":"Gerhard","family":"Weiss","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,1,9]]},"reference":[{"key":"286_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel P, Ng AY (2004) Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the 21st international conference on Machine learning, ICML \u201904, ACM, New York, NY, USA","DOI":"10.1145\/1015330.1015430"},{"key":"286_CR2","unstructured":"Ammar HB, Taylor ME, Tuyls K, Driessens K, Weiss G (2012) Reinforcement learning transfer via sparse coding (full paper). In: Proceedings of the 11th conference on Autonomous Agents and Multiagent Systems (AAMAS), Valencia"},{"issue":"5","key":"286_CR3","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"BD Argall","year":"2009","unstructured":"Argall BD, Chernova S, Veloso M, Browning B (2009) A survey of robot learning from demonstration. Robot Auton Syst, 57(5):469\u2013483","journal-title":"Robot Auton Syst"},{"key":"286_CR4","doi-asserted-by":"crossref","unstructured":"Bu\u015foniu L, Babu\u0161ka R, De Schutter B, Ernst D (2010) Reinforcement learning and dynamic programming using function approximators. CRC Press, Boca Raton","DOI":"10.1201\/9781439821091"},{"key":"286_CR5","unstructured":"Castro PS, Precup D (2010) Using bisimulation for policy transfer in mdps. In: Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: Volume 1, AAMAS \u201910, International Foundation for Autonomous Agents and Multiagent Systems, Richland, pp 1399\u20131400"},{"key":"286_CR6","unstructured":"Ferns N, Panangaden P, Precup D (2004) Metrics for finite markov decision processes. In: Chickering DM, Halpern JY, (eds), UAI, AUAI Press pp 162\u2013169"},{"issue":"6","key":"286_CR7","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1137\/10080484X","volume":"40","author":"N Ferns","year":"2011","unstructured":"Ferns N, Panangaden P, Precup D (2011) Bisimulation metrics for continuous markov decision processes. SIAM J Comput, 40(6):1662\u20131714","journal-title":"SIAM J Comput"},{"key":"286_CR8","doi-asserted-by":"crossref","unstructured":"Knox WB, Stone P, Breazeal C (2013) Teaching agents with human feedback: a demonstration of the tamer framework. In: IUI Companion, pp 65\u201366","DOI":"10.1145\/2451176.2451201"},{"key":"286_CR9","doi-asserted-by":"crossref","unstructured":"Lee H, Battle A, Raina R, Ng AY (2007) Efficient sparse coding algorithms. In: In NIPS, NIPS pp 801\u2013808","DOI":"10.7551\/mitpress\/7503.003.0105"},{"key":"286_CR10","unstructured":"Ng AY, Harada D, Russell S (1999) Policy invariance under reward transformations: theory and application to reward shaping. In: In Proceedings of the 16th International Conference on Machine Learning, Morgan Kaufmann, pp 278\u2013287"},{"key":"286_CR11","unstructured":"Snelson E, Ghahramani Z (2006) Sparse gaussian processes using pseudo-inputs. In: Advances in Neural Information Processing Systems, MIT press, pp 1257\u20131264"},{"key":"286_CR12","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor ME, Stone P (2009) Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res, 10:1633\u20131685","journal-title":"J Mach Learn Res"},{"issue":"1","key":"286_CR13","first-page":"2125","volume":"8","author":"ME Taylor","year":"2007","unstructured":"Taylor ME, Stone P, Liu Y (2007) Transfer learning via inter-task mappings for temporal difference learning. J Mach Learn Res 8(1):2125\u20132167","journal-title":"J Mach Learn Res"}],"container-title":["KI - K\u00fcnstliche Intelligenz"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13218-013-0286-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13218-013-0286-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13218-013-0286-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T14:16:52Z","timestamp":1688912212000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13218-013-0286-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,1,9]]},"references-count":13,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,2]]}},"alternative-id":["286"],"URL":"https:\/\/doi.org\/10.1007\/s13218-013-0286-8","relation":{},"ISSN":["0933-1875","1610-1987"],"issn-type":[{"value":"0933-1875","type":"print"},{"value":"1610-1987","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,1,9]]}}}