{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T21:17:29Z","timestamp":1768425449532,"version":"3.49.0"},"reference-count":45,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342288","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"5582-5589","source":"Crossref","is-referenced-by-count":2,"title":["A Multiplicative Value Function for Safe and Efficient Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Nick","family":"B\u00fchrer","sequence":"first","affiliation":[{"name":"ETH Zurich,Computer Vision Lab,Switzerland"}]},{"given":"Zhejun","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH Zurich,Computer Vision Lab,Switzerland"}]},{"given":"Alexander","family":"Liniger","sequence":"additional","affiliation":[{"name":"ETH Zurich,Computer Vision Lab,Switzerland"}]},{"given":"Fisher","family":"Yu","sequence":"additional","affiliation":[{"name":"ETH Zurich,Computer Vision Lab,Switzerland"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"ETH Zurich,Computer Vision Lab,Switzerland"}]}],"member":"263","reference":[{"key":"ref1","author":"Mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","author":"Berner","year":"2019","journal-title":"Dota 2 with large scale deep reinforcement learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064284"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"issue":"1","key":"ref10","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref11","author":"Srinivasan","year":"2020","journal-title":"Learning to be safe: Deep rl with a safety critic"},{"key":"ref12","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"ICML","author":"Stooke","year":"2020"},{"key":"ref13","first-page":"22","article-title":"Constrained policy optimization","volume-title":"ICML","author":"Achiam","year":"2017"},{"key":"ref14","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref15","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"ICML","author":"Haarnoja","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/614"},{"key":"ref17","author":"Gu","year":"2022","journal-title":"A review of safe reinforcement learning: Methods, theory and applications"},{"key":"ref18","article-title":"Reward constrained policy optimization","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Tessler","year":"2019"},{"key":"ref19","article-title":"Constrained reinforcement learning has zero duality gap","volume":"32","author":"Paternain","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref20","author":"Ray","year":"2019","journal-title":"Benchmarking Safe Exploration in Deep Reinforcement Learning"},{"key":"ref21","author":"Ma","year":"2021","journal-title":"Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17272"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575205"},{"key":"ref24","article-title":"Projection-based constrained policy optimization","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Yang","year":"2020"},{"key":"ref25","first-page":"15338","article-title":"First order constrained optimization in policy space","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref27","first-page":"11480","article-title":"Crpo: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"ICML","author":"Xu","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref29","first-page":"20423","article-title":"Saut\u00e9 rl: Almost surely safe reinforcement learning using state augmentation","volume-title":"ICML","author":"Sootla","year":"2022"},{"key":"ref30","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"30","author":"Berkenkamp","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref31","article-title":"Safe policy learning for continuous control","volume-title":"Conference on Robot Learning","author":"Chow","year":"2020"},{"key":"ref32","author":"Huh","year":"2020","journal-title":"Safe reinforcement learning for probabilistic reachability and safety specifications: A lyapunov-based approach"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084685"},{"key":"ref34","first-page":"10630","article-title":"Safe reinforcement learning using advantage-based intervention","volume-title":"ICML","author":"Wagener","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2022.3175628"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103811"},{"key":"ref39","article-title":"Model-free safe control for zero-violation reinforcement learning","volume-title":"Conference on Robot Learning","author":"Zhao","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109597"},{"key":"ref41","first-page":"9797","article-title":"Safe reinforcement learning in constrained markov decision processes","volume-title":"ICML","author":"Wachi","year":"2020"},{"key":"ref42","volume-title":"Constrained optimization and Lagrange multiplier methods","author":"Bertsekas","year":"2014"},{"key":"ref43","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Schulman","year":"2016"},{"key":"ref44","author":"Brockman","year":"2016","journal-title":"Openai gym"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"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\/10342288.pdf?arnumber=10342288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:15:20Z","timestamp":1703013320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342288","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}