{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:40:14Z","timestamp":1781973614890,"version":"3.54.5"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9029959","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T00:43:11Z","timestamp":1584060191000},"page":"5330-5337","source":"Crossref","is-referenced-by-count":2,"title":["Topological Approximate Dynamic Programming under Temporal Logic Constraints"],"prefix":"10.1109","author":[{"given":"Lening","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proceedings of the Sixteenth International Conference on Machine Learning ICML ’99"},{"key":"ref12","author":"bertsekas","year":"2000","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref13","first-page":"181","article-title":"Topological value iteration algorithms","volume":"42","author":"dai","year":"2011","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815215"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462967"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581505"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011254632723"},{"key":"ref18","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","author":"nachum","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref4","author":"baier","year":"2008","journal-title":"Principles of Model Checking (Representation and Mind Series)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2298143"},{"key":"ref6","first-page":"3630","article-title":"Probably approximately correct learning in stochastic games with temporal logic specifications","author":"wen","year":"2016","journal-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence IJCAI’16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.039"},{"key":"ref8","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proceedings of the 12th International Conference on Neural Information Processing Systems NIPS’99"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11797","article-title":"Safe reinforcement learning via shielding","author":"alshiekh","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref2","first-page":"27","author":"belta","year":"2017","journal-title":"Temporal Logics and Automata"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4222-2"},{"key":"ref9","first-page":"1008","article-title":"Actor-citic agorithms","author":"konda","year":"1999","journal-title":"Proceedings of the 12th International Conference on Neural Information Processing Systems NIPS’99"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2004.11.008"},{"key":"ref22","first-page":"243","author":"tadi?","year":"2006","journal-title":"Randomized Algorithms for Semi-Infinite Programming Problems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/moor.16.3.580"},{"key":"ref23","author":"bertsekas","year":"2016","journal-title":"Nonlinear Programming"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","location":"Nice, France","start":{"date-parts":[[2019,12,11]]},"end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09029959.pdf?arnumber=9029959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T11:01:54Z","timestamp":1695898914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9029959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9029959","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}