{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:40:30Z","timestamp":1767339630071,"version":"3.37.3"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"publisher","award":["HR001120C0036"],"award-info":[{"award-number":["HR001120C0036"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160557","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"5515-5521","source":"Crossref","is-referenced-by-count":7,"title":["Explainable Action Advising for Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yue","family":"Guo","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Campbell","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Stepputtis","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiyu","family":"Li","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dana","family":"Hughes","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Fang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katia","family":"Sycara","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Interactive teaching strategies for agent training","year":"2016","author":"amir","key":"ref13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/make1010002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21671-8_5"},{"key":"ref15","first-page":"629","article-title":"Action advising with advice imitation in deep reinforcement learning","author":"ilhan","year":"0","journal-title":"Proceedings of the AAMAS Conference"},{"key":"ref14","article-title":"Teacher-student framework: a reinforcement learning approach","author":"zimmer","year":"0","journal-title":"AAMAS Workshop Autonomous Robots and Multirobot Systems"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref31"},{"key":"ref30","article-title":"Half field offense: An environment for multiagent learning and ad hoc teamwork","volume":"3","author":"hausknecht","year":"0","journal-title":"The AAMAS Workshop on Adaptive and Learning Agents"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref33","first-page":"784","article-title":"Transfer learning for human navigation and triage strategies prediction in a sim-ulated urban search and rescue task","author":"guo","year":"0","journal-title":"2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1803_3"},{"key":"ref32","first-page":"270","article-title":"Developing a testbed for studying human-robot interaction in urban search and rescue","author":"lewis","year":"2019","journal-title":"Human-Centered Computing"},{"key":"ref2","first-page":"1053","article-title":"Teaching on a budget: Agents advising agents in reinforcement learning","author":"torrey","year":"0","journal-title":"Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09430-0"},{"key":"ref17","article-title":"Learning hierarchical teaching policies for cooperative agents","author":"kim","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref16","first-page":"1100","article-title":"Simultaneously learning and advising in multiagent reinforcement learning","author":"da silva","year":"0","journal-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967849"},{"key":"ref18","first-page":"17037","article-title":"An efficient transfer learning framework for multiagent reinforcement learning","volume":"34","author":"yang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2018.00018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16823"},{"key":"ref26","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics JMLR Workshop and Conference Proceedings"},{"key":"ref25","article-title":"Verifiable reinforcement learning via policy extraction","author":"bastani","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8847988"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13445"},{"key":"ref21","article-title":"Hammer: Multi-level coordination of reinforcement learning agents via learned messaging","author":"gupta","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"UC Berkeley CS188 intro to AI","author":"denero","year":"0","journal-title":"University Of California Berkeley"},{"key":"ref29","first-page":"72","article-title":"Half field offense in robocup soccer: A multiagent reinforcement learning case study","author":"kalyanakrishnan","year":"2006","journal-title":"Robot Soccer World Cup"},{"key":"ref8","article-title":"Rein-forcement learning from imperfect demonstrations","author":"gao","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.01.121"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1108\/JWAM-10-2015-003"},{"key":"ref4","first-page":"1674","article-title":"Learning by reusing previous advice in teacher-student paradigm","author":"zhu","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016128"},{"key":"ref6","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6036"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160557.pdf?arnumber=10160557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:35:54Z","timestamp":1690220154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160557","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}