{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T05:03:37Z","timestamp":1729659817446,"version":"3.28.0"},"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\/ssci44817.2019.9002777","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:49:24Z","timestamp":1582271364000},"page":"86-93","source":"Crossref","is-referenced-by-count":2,"title":["Multi-agent Reinforcement Learning in Spatial Domain Tasks using Inter Subtask Empowerment Rewards"],"prefix":"10.1109","author":[{"given":"Shubham","family":"Pateria","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Budhitama","family":"Subagdja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ah-Hwee","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889624"},{"key":"ref11","article-title":"Coordinated reinforcement learning","author":"guestrin","year":"0","journal-title":"CiteSeer"},{"key":"ref12","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"kok","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2011.6037325"},{"article-title":"Inequity aversion resolves intertemporal social dilemmas","year":"2018","author":"hughes","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref16","first-page":"709","article-title":"Optimal policy switching algorithms for reinforcement learning","author":"comanici","year":"2010","journal-title":"Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems Volume 1-Volume 1"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1142\/9789812777263_0020"},{"key":"ref4","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"AAAI"},{"key":"ref3","first-page":"2523","article-title":"Learning for decentralized control of multiagent systems in large, partiallyobservable stochastic environments","author":"liu","year":"2016","journal-title":"AAAI"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"sunehag","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2013.6719367"},{"key":"ref7","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376302"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-006-7035-4"},{"key":"ref9","first-page":"1","article-title":"Feudal multi-agent hierarchies for cooperative reinforcement learning","author":"ahilan","year":"2019","journal-title":"Workshop on Structure & Priors in Reinforcement Learning (SPiRL 2019) at ICLR 2019"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref22","first-page":"271","article-title":"Feudal reinforcement learning","author":"dayan","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"article-title":"Feudal networks for hierarchical reinforcement learning","year":"2017","author":"vezhnevets","key":"ref23"}],"event":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2019,12,6]]},"location":"Xiamen, China","end":{"date-parts":[[2019,12,9]]}},"container-title":["2019 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8975711\/9002648\/09002777.pdf?arnumber=9002777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T05:06:46Z","timestamp":1665896806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9002777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ssci44817.2019.9002777","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}