{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T04:07:17Z","timestamp":1751861237694},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812285","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"5511-5517","source":"Crossref","is-referenced-by-count":4,"title":["Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Sheng","family":"Li","sequence":"first","affiliation":[{"name":"Stanford University,Department of Aeronautics and Astronautics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ross","family":"Allen","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Lincoln Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mykel J.","family":"Kochenderfer","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Aeronautics and Astronautics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","author":"jaques","year":"2019","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref12"},{"key":"ref13","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref17","article-title":"Fast and accurate reading comprehension by combining self-attention and convolution","author":"yu","year":"2018","journal-title":"In-ternational Conference on Learning Representations (ICLR)"},{"key":"ref18","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"International Con-ference on Machine Learning (ICML) PMLR"},{"journal-title":"Attentional policies for cross-context multi-agent reinforcement learning","year":"2019","author":"wright","key":"ref19"},{"journal-title":"Multiagent bidirectionally-coordinated nets Emergence of human-level coordination in learning to play starcraft combat games","year":"2017","author":"peng","key":"ref4"},{"key":"ref3","first-page":"1538","article-title":"Tarmac: Targeted multi-agent communication","author":"das","year":"2019","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref6","article-title":"Deep implicit coordination graphs for multi-agent reinforcement learning","author":"li","year":"2021","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref5","first-page":"7254","article-title":"Learning attentional commu-nication for multi -agent cooperation","author":"jiang","year":"2018","journal-title":"Advances in Neural Information Processing Systems (Ne u rIPS)"},{"key":"ref8","article-title":"Emergent communication in a multi-modal, multi-step referential game","author":"evtimova","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1053"},{"key":"ref2","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"singh","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref9","article-title":"On the pitfalls of measuring emergent communication","author":"lowe","year":"2019","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref1","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref20","article-title":"Graph convo-lutional reinforcement learning","author":"jiang","year":"2020","journal-title":"International Con-ference on Learning Representations"},{"journal-title":"Pettingzoo Gym for multi-agent reinforcement learning","year":"2020","author":"terry","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/147470490800600318"},{"journal-title":"A paradigm for situated and goal-driven language learning","year":"2016","author":"gauthier","key":"ref23"},{"key":"ref25","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2022,5,23]]},"location":"Philadelphia, PA, USA","end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812285.pdf?arnumber=9812285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:06:25Z","timestamp":1667516785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812285","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}