{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:59:54Z","timestamp":1730195994150,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"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":[[2023,9,26]]},"DOI":"10.1109\/allerton58177.2023.10313475","type":"proceedings-article","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T13:48:25Z","timestamp":1699969705000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Inverse Reinforcement Learning with Learning and Leveraging Demonstrators\u2019 Varying Expertise Levels"],"prefix":"10.1109","author":[{"given":"Somtochukwu","family":"Oguchienti","sequence":"first","affiliation":[{"name":"Purdue University,School of Electrical and Computer Engineering,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahsa","family":"Ghasemi","sequence":"additional","affiliation":[{"name":"Purdue University,School of Electrical and Computer Engineering,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","author":"macglashan","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref12","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"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref34"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9682961"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v31i1.15956"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"ref11","first-page":"5","article-title":"Combining manual feedback with subsequent MDP reward signals for reinforcement learning","author":"knox","year":"2010","journal-title":"AAMAS"},{"key":"ref33","volume":"1","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref10","first-page":"79","article-title":"Design Principles for Creating Human-Shapable Agents","author":"knox","year":"2009","journal-title":"AAAI Spring Symposium on Agents that Learn from Human Teachers"},{"key":"ref32","article-title":"Playing hard exploration games by watching YouTube","volume":"31","author":"aytar","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","author":"brown","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2891173"},{"key":"ref17","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"617","article-title":"Integrating reinforcement learning with human demonstrations of varying ability","volume":"2","author":"taylor","year":"2011","journal-title":"The 10th International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref19","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"article-title":"Learning robust rewards with adversarial inverse reinforcement learning","year":"2017","author":"fu","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_8"},{"journal-title":"Batch active preference-based learning of reward functions","year":"2017","author":"sadigh","key":"ref23"},{"article-title":"Score-based inverse reinforcement learning","year":"2016","author":"el asri","key":"ref26"},{"key":"ref25","first-page":"519","article-title":"Batch active preference-based learning of reward functions","author":"biyik","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref20","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","volume":"24","author":"levine","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Reward learning from human preferences and demonstrations in Atari","volume":"31","author":"ibarz","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","year":"2020","author":"levine","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10411"},{"article-title":"Benchmarks and algorithms for offline preference-based reward learning","year":"2023","author":"shin","key":"ref29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref7","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref4","first-page":"12340","article-title":"Confidence-aware imitation learning from demonstrations with varying optimality","volume":"34","author":"zhang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","author":"brown","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref6","first-page":"1262","article-title":"Learning from suboptimal demonstration via self-supervised reward regression","author":"chen","year":"2021","journal-title":"Conference on Robot Learning"},{"key":"ref5","first-page":"1732","article-title":"Imitation learning by estimating expertise of demonstrators","author":"beliaev","year":"2022","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","start":{"date-parts":[[2023,9,26]]},"location":"Monticello, IL, USA","end":{"date-parts":[[2023,9,29]]}},"container-title":["2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10313338\/10313355\/10313475.pdf?arnumber=10313475","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T11:38:38Z","timestamp":1701257918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10313475\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,26]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/allerton58177.2023.10313475","relation":{},"subject":[],"published":{"date-parts":[[2023,9,26]]}}}