{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:36:00Z","timestamp":1725694560771},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008122","name":"Institute of Information & Communications Technology Planning & Evaluation (IITP)","doi-asserted-by":"publisher","award":["2019-0-01190"],"award-info":[{"award-number":["2019-0-01190"]}],"id":[{"id":"10.13039\/501100008122","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341973","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"7568-7573","source":"Crossref","is-referenced-by-count":0,"title":["Dual Variable Actor-Critic for Adaptive Safe Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Junseo","family":"Lee","sequence":"first","affiliation":[{"name":"Graduate School of Artificial Intelligence (GSAI) and ASRI, Seoul National University,Seoul,Korea"}]},{"given":"Jaeseok","family":"Heo","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Enginnering and ASRI,Seoul,Korea"}]},{"given":"Dohyeong","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Enginnering and ASRI,Seoul,Korea"}]},{"given":"Gunmin","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Enginnering and ASRI,Seoul,Korea"}]},{"given":"Songhwai","family":"Oh","sequence":"additional","affiliation":[{"name":"Graduate School of Artificial Intelligence (GSAI) and ASRI, Seoul National University,Seoul,Korea"}]}],"member":"263","reference":[{"article-title":"Mastering Atari with discrete world models","volume-title":"Proc. of the International Conference on Learning Representations","author":"Hafner","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"article-title":"Agent57: Outperforming the Atari human benchmark","volume-title":"Proc. of the International Conference on Machine Learning","author":"Badia","key":"ref3"},{"article-title":"Discovering and achieving goals via world models","volume-title":"Proc. of the Advances in Neural Information Processing Systems","author":"Mendonca","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iros45743.2020.9341123"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s001860050035"},{"article-title":"Learning to walk in the real world with minimal human effort","volume-title":"Proc. of the Conference on Robot Learning","author":"Ha","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17272"},{"article-title":"Responsive safety in rein-forcement learning by PID Lagrangian Methods","volume-title":"Proc. of the International Conference on Machine Learning","author":"Stooke","key":"ref10"},{"article-title":"Constrained policy optimization","volume-title":"Proc. of the International Conference on Machine Learning","author":"Achiam","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184793"},{"article-title":"Dynamic weights in multi-objective deep reinforcement learning","volume-title":"Proc. of the International Conference on Machine Learning","author":"Abels","key":"ref13"},{"article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume-title":"Proc. of the Advances in Neural Information Processing Systems","author":"Yang","key":"ref14"},{"article-title":"A constrained multi-objective reinforcement learning framework","volume-title":"Proc. of the Conference on Robot Learning","author":"Huang","key":"ref15"},{"article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Proc. of the Advances in Neural Information Processing Systems","author":"Paternain","key":"ref16"},{"article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. of the International Conference on Machine Learning","author":"Haarnoja","key":"ref17"},{"article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. of the Advances in Neural Information Processing Systems","author":"Kumar","key":"ref18"},{"key":"ref19","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019","journal-title":"CoRR, vol. abs\/1910.01708"},{"article-title":"Constrained variational policy optimization for safe reinforcement learning","volume-title":"Proc. of the International Conference on Machine Learning","author":"Liu","key":"ref20"},{"volume-title":"Jackal UGV - small weatherproof robot - Clearpath","year":"2020","key":"ref21"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341973.pdf?arnumber=10341973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:27:40Z","timestamp":1703032060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341973","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}