{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T11:53:33Z","timestamp":1774698813866,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"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":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10384223","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"2372-2378","source":"Crossref","is-referenced-by-count":4,"title":["Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Patrick","family":"Emami","sequence":"first","affiliation":[{"name":"National Renewable Energy Laboratory,Golden,CO,USA,80401"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Renewable Energy Laboratory,Golden,CO,USA,80401"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Biagioni","sequence":"additional","affiliation":[{"name":"Maplewell Energy,Broomfield,CO,USA,80021"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed S.","family":"Zamzam","sequence":"additional","affiliation":[{"name":"National Renewable Energy Laboratory,Golden,CO,USA,80401"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Papoudakis","year":"2019","journal-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning"},{"key":"ref2","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","author":"Hernandez-Leal","year":"2017","journal-title":"vol. abs\/1707.09183"},{"key":"ref3","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environ-ments","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Lowe","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073663"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304323"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref9","first-page":"4045","article-title":"Time limits in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pardo","year":"2018"},{"key":"ref10","author":"Wang","year":"2020","journal-title":"R-maddpg for partially observable environments and limited communication"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2022.108830"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119067"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.812782"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CAMSAP.2011.6135903"},{"key":"ref15","first-page":"3254","article-title":"Reinforcement learning for control with multiple frequencies","volume":"33","author":"Lee","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","first-page":"195","article-title":"Planning, learning and coordination in multiagent deci-sion processes","volume":"96","author":"Boutilier","year":"1996","journal-title":"TARK"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12105"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3412841.3441953"},{"key":"ref19","author":"Biagioni","year":"2022","journal-title":"From model-based to model-free: Learning building control for demand response"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","location":"Singapore, Singapore","start":{"date-parts":[[2023,12,13]]},"end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10384223.pdf?arnumber=10384223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:46:21Z","timestamp":1706028381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10384223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10384223","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}