{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T18:34:22Z","timestamp":1729622062499,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":[[2019,8]]},"DOI":"10.1109\/coase.2019.8843223","type":"proceedings-article","created":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T00:08:11Z","timestamp":1568938091000},"page":"257-262","source":"Crossref","is-referenced-by-count":3,"title":["Constructive Policy: Reinforcement Learning Approach for Connected Multi-Agent Systems"],"prefix":"10.1109","author":[{"given":"Sayyed Jaffar Ali","family":"Raza","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref38","article-title":"Modular multitask reinforcement learning with policy sketches","author":"andreas","year":"2016","journal-title":"arXiv preprint arXiv 1611 02792"},{"key":"ref33","article-title":"Realworld modeling of a pathfinding robot using robot operating system (ros)","author":"raza","year":"2018","journal-title":"arXiv preprint arXiv 1802 10363"},{"key":"ref32","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509772"},{"key":"ref30","article-title":"A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning","author":"brochu","year":"2010","journal-title":"arXiv preprint arXiv 1012 2599"},{"key":"ref37","first-page":"816","article-title":"Identifying useful subgoals in reinforcement learning by local graph partitioning","author":"?im?ek","year":"2005","journal-title":"Proceedings of the 22nd International Conference on Machine Learning"},{"key":"ref36","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","author":"chebotar","year":"2017","journal-title":"arXiv preprint arXiv l703 03078"},{"key":"ref34","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref10","first-page":"769","article-title":"Hierarchical apprenticeship learning with application to quadruped locomotion","author":"kolter","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref40","first-page":"252","article-title":"Multi-agent reinforcement learning: A modular approach","author":"ono","year":"1996","journal-title":"Proceedings of the Second International Conference on Multiagent Systems"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2017","author":"lillicrap","key":"ref12"},{"key":"ref13","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"2017","journal-title":"arXiv preprint arXiv 1702 08502"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"journal-title":"Development of a loca prosthetic limb using artificial intelligence","year":"2016","author":"alshamsi","key":"ref15"},{"key":"ref16","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"arXiv preprint arXiv 1704 03012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509336"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref19","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","author":"chentanez","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCT.2019.8710861"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50052-9"},{"key":"ref3","article-title":"Reinforcement learning and the reward engineering principle","author":"dewey","year":"2014","journal-title":"2014 AAAI Spring Symposium Series"},{"key":"ref27","first-page":"227","article-title":"Coordinated reinforcement learning","volume":"2","author":"guestrin","year":"2002","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref29","article-title":"Towards adapting deep visuomotor representations from simulated to real environments","volume":"abs l511 7111","author":"tzeng","year":"2015","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref7","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref20","article-title":"Semi-markov decision processes","author":"baykal-g\u00fcrsoy","year":"2010","journal-title":"The Wiley Encyclopedia of Operations Research and Management Sceience"},{"key":"ref22","article-title":"Meta learning shared hierarchies","author":"frans","year":"2017","journal-title":"arXiv preprint arXiv 1710 09767"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"2555","DOI":"10.1007\/978-0-387-74759-0_440","article-title":"Neuro-dynamic programming","author":"bertsekas","year":"2008","journal-title":"Encyclopedia of Optimization"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2006.05.003"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref23","first-page":"39","article-title":"Analysis of thompson sampling for the multi-armed bandit problem","author":"agrawal","year":"2012","journal-title":"Conference on Learning Theory"},{"key":"ref26","first-page":"1547","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094427"}],"event":{"name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2019,8,22]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2019,8,26]]}},"container-title":["2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8827189\/8842826\/08843223.pdf?arnumber=8843223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T02:55:10Z","timestamp":1664420110000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8843223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/coase.2019.8843223","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}