{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:08:08Z","timestamp":1737176888564,"version":"3.33.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825427","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"4884-4891","source":"Crossref","is-referenced-by-count":0,"title":["Robot See, Robot Do: Imitation Reward for Noisy Financial Environments"],"prefix":"10.1109","author":[{"given":"Sven","family":"Golu\u017ea","sequence":"first","affiliation":[{"name":"University of Zagreb Faculty of Electrical Engineering and Computing,Laboratory for Financial and Risk Analytics,Zagreb,Croatia,10000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomislav","family":"Kova\u010devi\u0107","sequence":"additional","affiliation":[{"name":"University of Zagreb Faculty of Electrical Engineering and Computing,Laboratory for Financial and Risk Analytics,Zagreb,Croatia,10000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stjepan","family":"Begu\u0161i\u0107","sequence":"additional","affiliation":[{"name":"University of Zagreb Faculty of Electrical Engineering and Computing,Laboratory for Financial and Risk Analytics,Zagreb,Croatia,10000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zvonko","family":"Kostanj\u010dar","sequence":"additional","affiliation":[{"name":"University of Zagreb Faculty of Electrical Engineering and Computing,Laboratory for Financial and Risk Analytics,Zagreb,Croatia,10000"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.1986.tb04513.x"},{"key":"ref3","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning","volume":"1","author":"Ng"},{"key":"ref4","first-page":"674","article-title":"Reward Estimation for Variance Reduction in Deep Reinforcement Learning","volume-title":"Proceedings of Machine Learning Research","volume":"87","author":"Romoff"},{"key":"ref5","article-title":"Goal-conditioned imitation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Ding"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932789"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5587"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2017\/656","article-title":"Reinforcement Learning with a Corrupted Reward Channel","author":"Everitt","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557283"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"ref12","first-page":"4300","article-title":"Deep reinforcement learning from human preferences","volume-title":"Advances in Neural Information Processing Systems","volume":"2017-Decem","author":"Christiano"},{"key":"ref13","first-page":"6766","article-title":"Inverse reward design","volume-title":"Advances in Neural Information Processing Systems","volume":"2017-Decem","author":"Hadfield-Menell"},{"key":"ref14","first-page":"693","article-title":"A distributional perspective on reinforcement learning","volume-title":"34th International Conference on Machine Learning, ICML 2017","volume":"1","author":"Bellemare"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213246"},{"article-title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Reddy","key":"ref16"},{"article-title":"Imitation Learning by Reinforcement Learning","volume-title":"ICLR 2022 - 10th International Conference on Learning Representations","author":"Ciosek","key":"ref17"},{"article-title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","volume-title":"The Twelfth International Conference on Learning Representations, ICLR","author":"Luo","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO57284.2023.10159778"},{"key":"ref20","first-page":"627","article-title":"No-regret reductions for imitation learning and structured prediction","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics","author":"Ross"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref22","first-page":"368","article-title":"Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision","volume-title":"Proceedings of Machine Learning Research","volume":"205","author":"Hoque"},{"article-title":"Generative adversarial imitation learning","volume-title":"Advances in Neural Information Processing Systems","author":"Ho","key":"ref23"},{"article-title":"Learning robust rewards with adversarial inverse reinforcement learning","volume-title":"6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings. International Conference on Learning Representations, ICLR","author":"Fu","key":"ref24"},{"key":"ref25","first-page":"11 364","article-title":"Random expert distillation: Imitation learning via expert policy support estimation","volume-title":"36th International Conference on Machine Learning, ICML 2019","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3303283"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-024-09593-6"},{"volume-title":"Technical analysis of the financial markets: A comprehensive guide to trading methods and applications","year":"1999","author":"Murphy","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3905\/jfds.2020.1.030"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref30"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825427.pdf?arnumber=10825427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:14:40Z","timestamp":1737101680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825427","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}