{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:46:27Z","timestamp":1770846387402,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343086","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"4163-4170","source":"Crossref","is-referenced-by-count":0,"title":["Constrained Policy Optimization with Approximately Monotonically Increasing Rewards"],"prefix":"10.1109","author":[{"given":"Yuanyang","family":"Lu","sequence":"first","affiliation":[{"name":"Nanjing University,School of Management and Engineering,Department of Control Science and Intelligence Engineering,Nanjing,China,210093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiqiao","family":"Fu","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Management and Engineering,Department of Control Science and Intelligence Engineering,Nanjing,China,210093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing University,Center for Advanced Control and Smart Operations (CACSO),Suzhou,China,215163"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Management and Engineering,Department of Control Science and Intelligence Engineering,Nanjing,China,210093"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/328"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-14174-5_16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"issue":"167","key":"ref7","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","article-title":"Reward constrained policy optimization","volume-title":"International Conference on Learning Representations","author":"Tessler"},{"key":"ref9","first-page":"7555","article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Advances in Neural Information Processing Systems.","author":"Paternain","year":"2019"},{"key":"ref10","first-page":"3703","article-title":"Batch policy learning under constraints","volume-title":"International Conference on Machine Learning","author":"Le"},{"key":"ref11","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International Conference on Machine Learning","author":"Achiam"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/54"},{"key":"ref14","article-title":"Projection-based constrained policy optimization","volume-title":"International Conference on Learning Representations","author":"Yang"},{"key":"ref15","first-page":"15 338","article-title":"First order constrained optimization in policy space","volume-title":"Advances in Neural Information Processing Systems.","author":"Zhang","year":"2020"},{"key":"ref16","first-page":"18 964","article-title":"Safety gymnasium: A unified safe reinforcement learning benchmark","volume-title":"Advances in Neural Information Processing Systems.","author":"Ji","year":"2023"},{"key":"ref17","volume-title":"Reinforcement learning: An introduction.","author":"Sutton","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref19","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Kakade"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref21","first-page":"9111","article-title":"Constrained update projection approach to safe policy optimization","volume-title":"Advances in Neural Information Processing Systems.","author":"Yang","year":"2022"},{"key":"ref22","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343086.pdf?arnumber=11343086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:53:19Z","timestamp":1770843199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343086","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}