{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:36:09Z","timestamp":1729672569044,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"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":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683749","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T15:50:18Z","timestamp":1643730618000},"page":"5239-5246","source":"Crossref","is-referenced-by-count":3,"title":["Discrete-Time Mean Field Control with Environment States"],"prefix":"10.1109","author":[{"given":"Kai","family":"Cui","sequence":"first","affiliation":[{"name":"Technische Universität Darmstadt,Department of Electrical Engineering,Darmstadt,Germany,64287"}]},{"given":"Anam","family":"Tahir","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Department of Electrical Engineering,Darmstadt,Germany,64287"}]},{"given":"Mark","family":"Sinzger","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Department of Electrical Engineering,Darmstadt,Germany,64287"}]},{"given":"Heinz","family":"Koeppl","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Department of Electrical Engineering,Darmstadt,Germany,64287"}]}],"member":"263","reference":[{"key":"ref32","first-page":"3053","article-title":"Rllib: Abstractions for distributed reinforcement learning","author":"liang","year":"2018","journal-title":"International Conference on Machine Learning"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11586","article-title":"Decentralised learning in systems with many, many strategic agents","author":"mguni","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref11","first-page":"4966","article-title":"Learning mean-field games","author":"guo","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"1909","article-title":"Approximately solving mean field games via entropy-regularized deep reinforcement learning","author":"cui","year":"2021","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-010-9123-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-8508-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2014.6961476"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23425-0_9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2406973"},{"article-title":"Mckean-vlasov optimal control: the dynamic programming principle","year":"2019","author":"djete","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1051\/cocv\/2017019"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2997771"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"221","DOI":"10.4310\/CIS.2006.v6.n3.a5","article-title":"Large population stochastic dynamic games: closed-loop mckean-vlasov systems and the nash certainty equivalence principle","volume":"6","author":"huang","year":"2006","journal-title":"Communications in Information & Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpur.2009.10.010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11537-007-0657-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/17M1112583"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"article-title":"Mean-field markov decision processes with common noise and open-loop controls","year":"2019","author":"motte","key":"ref20"},{"article-title":"Mean-field controls with q-learning for cooperative marl: Convergence and complexity analysis","year":"2020","author":"gu","key":"ref22"},{"article-title":"Dynamic programming principles for learning mfcs","year":"2019","author":"gu","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/120889496"},{"journal-title":"Machine Learning A Probabilistic Perspective","year":"2012","author":"murphy","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2015.2428331"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2637347"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2021,12,14]]},"location":"Austin, TX, USA","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683749.pdf?arnumber=9683749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T08:59:40Z","timestamp":1674637180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683749","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}