{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:23:27Z","timestamp":1778786607746,"version":"3.51.4"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9982278","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"9034-9039","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Objective Policy Gradients with Topological Constraints"],"prefix":"10.1109","author":[{"given":"Kyle Hollins","family":"Wray","sequence":"first","affiliation":[{"name":"Stanford University,Stanford,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stas","family":"Tiomkin","sequence":"additional","affiliation":[{"name":"San Jose State University,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mykel J.","family":"Kochenderfer","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[{"name":"University of California,Berkeley,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/664"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2011.11.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575308"},{"key":"ref7","first-page":"482","author":"Florensa","year":"2017","journal-title":"Reverse curriculum generation for reinforcement learning"},{"key":"ref8","first-page":"9797","article-title":"Safe reinforcement learning in constrained Markov decision processes","volume-title":"International Conference on Machine Learning (ICML)","author":"Wac hi"},{"key":"ref9","volume-title":"Abstractions in reasoning for long-term autonomy","author":"Wray","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9647"},{"key":"ref11","author":"Achiam","year":"2017","journal-title":"Constrained policy optimization"},{"key":"ref12","article-title":"Learning to walk via deep reinforcement learning","author":"Haarnoja","year":"2018","journal-title":"ar Xiv preprint"},{"key":"ref13","volume-title":"Constrained Markov decision processes","author":"Altman","year":"1999"},{"key":"ref14","first-page":"197","article-title":"Multi-criteria reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"G\u00e1bor"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9647"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"ar Xiv preprint"},{"key":"ref17","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"Sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref18","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International Conference on Machine Learning (ICML)","author":"Schulman"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812262"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09982278.pdf?arnumber=9982278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:11:42Z","timestamp":1706767902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9982278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9982278","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}