{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:27:37Z","timestamp":1770917257203,"version":"3.50.1"},"reference-count":23,"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\/cig.2019.8847988","type":"proceedings-article","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T01:49:14Z","timestamp":1569548954000},"page":"1-8","source":"Crossref","is-referenced-by-count":20,"title":["Teaching on a Budget in Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ercument","family":"Ilhan","sequence":"first","affiliation":[]},{"given":"Jeremy","family":"Gow","sequence":"additional","affiliation":[]},{"given":"Diego","family":"Perez-Liebana","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Teacher-Student Framework: A Reinforcement Learning Approach","author":"zimmer","year":"2014","journal-title":"AAMAS Workshop Autonomous Robots and Multirobot Systems"},{"key":"ref11","first-page":"804","article-title":"Interactive Teaching Strategies for Agent Training","author":"amir","year":"2016","journal-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence IJCAI 2016"},{"key":"ref12","article-title":"Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer","author":"zhan","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/make1010002"},{"key":"ref14","first-page":"1100","article-title":"Simultaneously Learning and Advising in Multiagent Reinforcement Learning","author":"da silva","year":"2017","journal-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems ser AAMAS ’17"},{"key":"ref15","article-title":"Learning to Teach in Cooperative Multiagent Reinforcement Learning","author":"omidshafiei","year":"2018"},{"key":"ref16","article-title":"Learning Hierarchical Teaching in Cooperative Multiagent Reinforcement Learning","author":"kim","year":"2019","journal-title":"arXiv preprint arXiv 1903 03216"},{"key":"ref17","author":"oliehoek","year":"2016","journal-title":"A Concise Introduction to Decentralized POMDPs ser Springer Briefs in Intelligent Systems"},{"key":"ref18","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013"},{"key":"ref19","first-page":"3215","article-title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","author":"hessel","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)"},{"key":"ref4","article-title":"AlphaStar: Mastering the Real-Time Strategy Game StarCraft II","author":"vinyals","year":"2019"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the Game of Go with Deep Neural Networks and Tree Search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref5","first-page":"1633","article-title":"Transfer Learning for Reinforcement Learning Domains: A Survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"2625","article-title":"Policy Shaping: Integrating Human Feedback with Reinforcement Learning","author":"griffith","year":"2013","journal-title":"Neural Information Processing Systems"},{"key":"ref7","author":"clouse","year":"1996","journal-title":"On Integrating Apprentice Learning and Reinforcement Learning"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level Control Through Deep Reinforcement Learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","first-page":"1053","article-title":"Teaching on a Budget: Agents Advising Agents in Reinforcement Learning","author":"torrey","year":"2013","journal-title":"International conference on Autonomous Agents and Multi-Agent Systems AAMAS ’13"},{"key":"ref20","article-title":"Exploration by Random Network Distillation","author":"burda","year":"2018"},{"key":"ref22","first-page":"2137","article-title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","author":"foerster","year":"2016","journal-title":"Neural Information Processing Systems"},{"key":"ref21","author":"goodfellow","year":"2016","journal-title":"Deep Learning Adaptive Computation and Machine Learning series"},{"key":"ref23","article-title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","author":"tampuu","year":"2015"}],"event":{"name":"2019 IEEE Conference on Games (CoG)","location":"London, United Kingdom","start":{"date-parts":[[2019,8,20]]},"end":{"date-parts":[[2019,8,23]]}},"container-title":["2019 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8844551\/8847948\/08847988.pdf?arnumber=8847988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:47:04Z","timestamp":1658155624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8847988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8847988","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}