{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T05:16:41Z","timestamp":1735276601758,"version":"3.32.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002551","name":"Seoul National University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801577","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"2893-2898","source":"Crossref","is-referenced-by-count":0,"title":["Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards"],"prefix":"10.1109","author":[{"given":"Hyeokjin","family":"Kwon","sequence":"first","affiliation":[{"name":"Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826"}]},{"given":"Gunmin","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and ASRI,Seoul,Korea,08826"}]},{"given":"Junseo","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826"}]},{"given":"Songhwai","family":"Oh","sequence":"additional","affiliation":[{"name":"Seoul National University,Interdisciplinary Program in Artificial Intelligence and ASRI,Seoul,Korea,08826"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565085"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3450267.3450542"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341104"},{"article-title":"Learning a decision module by imitating driver\u2019s control behaviors","volume-title":"Proc. of the Conference on Robot Learning (CoRL)","author":"Huang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.102"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"article-title":"Constrained policy optimization","volume-title":"Proc. of the International Conference on Machine Learning (ICML)","author":"Achiam","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141829"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"issue":"1","key":"ref11","first-page":"2","article-title":"Benchmarking safe exploration in deep reinforcement learning","volume":"7","author":"Ray","year":"2019"},{"key":"ref12","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. of the International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Ross","key":"ref14"},{"article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Ziebart","key":"ref15"},{"key":"ref16","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-70139-4","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","volume":"30","author":"Li","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Primal Wasser-stein imitation learning","volume-title":"Proc. of the International Conference on Learning Representations (ICLR)","author":"Dadashi","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342038"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref20"},{"article-title":"WC-SAC: Worst-case soft actor critic for safety-constrained reinforcement learning","volume-title":"Proc. of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Yang","key":"ref21"},{"article-title":"Trust region policy optimization","volume-title":"Proc. of the International Conference on Machine Learning (ICML)","author":"Schulman","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184793"},{"key":"ref24","article-title":"Trust region-based safe distributional reinforcement learning for multiple constraints","volume":"36","author":"Kim","year":"2024","journal-title":"Advances in neural information processing systems"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. of the International Conference on Machine Learning (ICML)","author":"Haarnoja","key":"ref25"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801577.pdf?arnumber=10801577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:35:52Z","timestamp":1735198552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801577","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}