{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:35:05Z","timestamp":1730298905335,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T00:00:00Z","timestamp":1670112000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T00:00:00Z","timestamp":1670112000000},"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":[[2022,12,4]]},"DOI":"10.1109\/ssci51031.2022.10022174","type":"proceedings-article","created":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T20:05:39Z","timestamp":1675109139000},"page":"1545-1550","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Beyond-Demonstrator via Meta Learning-Based Reward Extrapolation"],"prefix":"10.1109","author":[{"given":"Mingqi","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Man-on","family":"Pun","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref2","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"International Conference on Machine Learning","volume":"1","author":"Ng","year":"2000"},{"journal-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","year":"2019","author":"Brown","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-55393-7_1"},{"key":"ref5","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","volume-title":"Conference on Robot Learning","author":"Brown","year":"2020"},{"journal-title":"Learning from suboptimal demonstration via self-supervised reward regression","year":"2020","author":"Chen","key":"ref6"},{"key":"ref7","first-page":"10925","article-title":"Intrinsic reward driven imitation learning via generative model","volume-title":"International Conference on Machine Learning","author":"Yu","year":"2020"},{"journal-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref8"},{"journal-title":"Large-scale study of curiosity-driven learning","year":"2018","author":"Burda","key":"ref9"},{"journal-title":"Episodic curiosity through reachability","year":"2018","author":"Savinov","key":"ref10"},{"key":"ref11","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International Conference on Machine Learning","author":"Finn","year":"2017"},{"journal-title":"Wasserstein adversarial imitation learning","year":"2019","author":"Xiao","key":"ref12"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref13"},{"volume-title":"Pytorch implementation of the reinforcement learning algorithms","year":"2018","key":"ref14"}],"event":{"name":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2022,12,4]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,7]]}},"container-title":["2022 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022049\/10022014\/10022174.pdf?arnumber=10022174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:33:57Z","timestamp":1707813237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,4]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/ssci51031.2022.10022174","relation":{},"subject":[],"published":{"date-parts":[[2022,12,4]]}}}