{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T04:31:36Z","timestamp":1746246696849,"version":"3.37.3"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176133","61836004"],"award-info":[{"award-number":["62176133","61836004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua\u2013Guoqiang Research Program","award":["2019GQG0006"],"award-info":[{"award-number":["2019GQG0006"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0200300"],"award-info":[{"award-number":["2021ZD0200300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shuimu Tsinghua Scholar Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tnnls.2022.3165941","type":"journal-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T20:42:08Z","timestamp":1650919328000},"page":"10359-10373","source":"Crossref","is-referenced-by-count":1,"title":["Partial Consistency for Stabilizing Undiscounted Reinforcement Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5161-5326","authenticated-orcid":false,"given":"Haichuan","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7908-9524","authenticated-orcid":false,"given":"Zhile","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9173-2984","authenticated-orcid":false,"given":"Tian","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9687-5263","authenticated-orcid":false,"given":"Tianren","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5013-1880","authenticated-orcid":false,"given":"Jinsheng","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3181-6881","authenticated-orcid":false,"given":"Shangqi","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Automation and the Department of Precision Instrument, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4813-2494","authenticated-orcid":false,"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Center for Brain-Inspired Computing Research, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3080521"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3087733"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2402203"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3023711"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3057958"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3079148"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v26i1.13773"},{"key":"ref13","first-page":"15254","article-title":"Meta-gradient reinforcement learning with an objective discovered online","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref14","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref15","article-title":"Simple random search provides a competitive approach to reinforcement learning","author":"Mania","year":"2018","journal-title":"arXiv:1803.07055"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11170"},{"key":"ref17","article-title":"Reward tweaking: Maximizing the total reward while planning for short horizons","author":"Tessler","year":"2020","journal-title":"arXiv:2002.03327v2"},{"key":"ref18","first-page":"2402","article-title":"Meta-gradient reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5784"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref20"},{"key":"ref21","first-page":"222","article-title":"Max-prob: An unbiased rational decision making procedure for multiple-adversary environments","volume-title":"Proc. 22nd Int. Joint Conf. Artif. Intell.","author":"Hashavit"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v21i1.13452"},{"key":"ref23","first-page":"4042","article-title":"Time limits in reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Pardo"},{"key":"ref24","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schulman"},{"key":"ref25","first-page":"14111","article-title":"Using a logarithmic mapping to enable lower discount factors in reinforcement learning","volume-title":"Annu. Conf. Neural Inf. Process. Syst.","author":"van Seijen"},{"key":"ref26","first-page":"2818","article-title":"Sample complexity of episodic fixed-horizon reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"28","author":"Dann"},{"key":"ref27","first-page":"269","article-title":"Discount factor as a regularizer in reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Amit"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341124"},{"key":"ref32","first-page":"21579","article-title":"Generating adjacency-constrained subgoals in hierarchical reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref33","first-page":"1","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sutton"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50045-9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/moor.16.3.580"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0562"},{"key":"ref37","first-page":"4180","article-title":"The dependence of effective planning horizon on model accuracy","volume-title":"Proc. 25th Int. Joint Conf. Artif. Intell.","author":"Jiang"},{"key":"ref38","first-page":"438","article-title":"A theory of goal-oriented MDPs with dead ends","volume-title":"Proc. 28th Conf. Uncertainty Artif. Intell.","author":"Kolobov"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10303"},{"key":"ref41","first-page":"1","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a GPU","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Babaeizadeh"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9701"},{"key":"ref45","first-page":"162","article-title":"Metrics for finite Markov decision processes","volume-title":"Proc. 20th Conf. Uncertainty Artif. Intell.","author":"Ferns"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29513-4_70"},{"key":"ref50","first-page":"1","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Int. Conf. Learn. Represent.","author":"Hafner"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107600"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10336252\/09762369.pdf?arnumber=9762369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:12:11Z","timestamp":1708110731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9762369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":51,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3165941","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}