Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning Over Noisy Channels

We propose a novel formulation of the "effectiveness problem" in communications, put forth by Shannon and Weaver in their seminal work " The Mathematical Theory of Communication ", by considering multiple agents communicating over a noisy channel in order to achieve better coordi...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE journal on selected areas in communications Vol. 39; no. 8; pp. 2590 - 2603
Main Authors:	Tung, Tze-Yang, Kobus, Szymon, Roig, Joan Pujol, Gunduz, Deniz
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.08.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Channel coding Channels Communication channels Communications systems Deep learning Drone vehicles error correction coding joint source-channel coding Learning to communicate Markov processes Modulation multi-agent systems Multiagent systems Noise measurement Protocols Reagents Reinforcement learning reinforcement learning (RL) Semantics Wireless communication
ISSN:	0733-8716, 1558-0008
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	We propose a novel formulation of the "effectiveness problem" in communications, put forth by Shannon and Weaver in their seminal work " The Mathematical Theory of Communication ", by considering multiple agents communicating over a noisy channel in order to achieve better coordination and cooperation in a multi-agent reinforcement learning (MARL) framework. Specifically, we consider a multi-agent partially observable Markov decision process (MA-POMDP), in which the agents, in addition to interacting with the environment, can also communicate with each other over a noisy communication channel. The noisy communication channel is considered explicitly as part of the dynamics of the environment, and the message each agent sends is part of the action that the agent can take. As a result, the agents learn not only to collaborate with each other but also to communicate "effectively" over a noisy channel. This framework generalizes both the traditional communication problem, where the main goal is to convey a message reliably over a noisy channel, and the "learning to communicate" framework that has received recent attention in the MARL literature, where the underlying communication channels are assumed to be error-free. We show via examples that the joint policy learned using the proposed framework is superior to that where the communication is considered separately from the underlying MA-POMDP. This is a very powerful framework, which has many real world applications, from autonomous vehicle planning to drone swarm control, and opens up the rich toolbox of deep reinforcement learning for the design of multi-user communication systems.
AbstractList	We propose a novel formulation of the "effectiveness problem" in communications, put forth by Shannon and Weaver in their seminal work " The Mathematical Theory of Communication ", by considering multiple agents communicating over a noisy channel in order to achieve better coordination and cooperation in a multi-agent reinforcement learning (MARL) framework. Specifically, we consider a multi-agent partially observable Markov decision process (MA-POMDP), in which the agents, in addition to interacting with the environment, can also communicate with each other over a noisy communication channel. The noisy communication channel is considered explicitly as part of the dynamics of the environment, and the message each agent sends is part of the action that the agent can take. As a result, the agents learn not only to collaborate with each other but also to communicate "effectively" over a noisy channel. This framework generalizes both the traditional communication problem, where the main goal is to convey a message reliably over a noisy channel, and the "learning to communicate" framework that has received recent attention in the MARL literature, where the underlying communication channels are assumed to be error-free. We show via examples that the joint policy learned using the proposed framework is superior to that where the communication is considered separately from the underlying MA-POMDP. This is a very powerful framework, which has many real world applications, from autonomous vehicle planning to drone swarm control, and opens up the rich toolbox of deep reinforcement learning for the design of multi-user communication systems.
Author	Roig, Joan Pujol Tung, Tze-Yang Kobus, Szymon Gunduz, Deniz
Author_xml	– sequence: 1 givenname: Tze-Yang orcidid: 0000-0003-2716-5211 surname: Tung fullname: Tung, Tze-Yang email: tze-yang.tung14@imperial.ac.uk organization: Department of Electrical and Electronic Engineering, Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K – sequence: 2 givenname: Szymon surname: Kobus fullname: Kobus, Szymon organization: Department of Electrical and Electronic Engineering, Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K – sequence: 3 givenname: Joan Pujol surname: Roig fullname: Roig, Joan Pujol organization: Samsung Electronics Research and Development Institute UK, Staines-upon-Thames, U.K – sequence: 4 givenname: Deniz surname: Gunduz fullname: Gunduz, Deniz organization: Department of Electrical and Electronic Engineering, Information Processing and Communications Laboratory (IPC-Lab), Imperial College London, London, U.K
BookMark	eNp9kE1PGzEURS0UpIaPH1CxsdT1BD97xvZ0F40IBQUi0bIeeZw31DRjU3uSiiX_nAlBCLpg9aSne-6VzgEZ-eCRkK_AJgCsPL38Oa0mnHGYCKYVz_UeGUNR6IwxpkdkzJQQmVYgv5CDlO4ZgzzXfEyeztoWbe82SKvQdWvvrOld8Ok7ndLL4HxP52iid_6OGr_8GKKzaDr8F-If2oZIr9ar3mXTOxygG3R--Fns8H3FYoORXgeXHmn123iPq3RE9luzSnj8eg_J7ezsV_Ujmy_OL6rpPLO8FH1mdG5NY2QLEhiyctmCNVAY1RTLpVRWgLYATWFVKRqhVIOgpSwVN7JsmUJxSL7teh9i-LvG1Nf3YR39MFnzouAgmSj5kIJdysaQUsS2foiuM_GxBlZvTddb0_XWdP1qemDUf4x1_YugPhq3-pQ82ZEOEd-WylzKgoF4Bl6PjvE
CODEN	ISACEM
CitedBy_id	crossref_primary_10_1109_TCOMM_2024_3385922 crossref_primary_10_1016_j_knosys_2024_112714 crossref_primary_10_1109_ACCESS_2022_3231039 crossref_primary_10_3390_electronics12234845 crossref_primary_10_1109_JSAC_2022_3221950 crossref_primary_10_1109_TMC_2024_3478048 crossref_primary_10_1016_j_oceaneng_2024_118225 crossref_primary_10_1109_JIOT_2024_3469279 crossref_primary_10_1109_TCOMM_2024_3487513 crossref_primary_10_1109_JIOT_2023_3312553 crossref_primary_10_1109_LCOMM_2022_3214792 crossref_primary_10_1109_TWC_2025_3543373 crossref_primary_10_1109_TCOMM_2023_3244958 crossref_primary_10_1109_TVT_2022_3195202 crossref_primary_10_1016_j_comcom_2023_12_002 crossref_primary_10_1109_TWC_2024_3464639 crossref_primary_10_1109_TCOMM_2023_3282256 crossref_primary_10_1109_TRO_2024_3431829 crossref_primary_10_1016_j_ins_2022_07_052 crossref_primary_10_1109_TMC_2024_3406375 crossref_primary_10_1109_TCOMM_2024_3365520 crossref_primary_10_1002_aaai_70023 crossref_primary_10_1016_j_jfranklin_2024_107032 crossref_primary_10_1109_JSAC_2022_3223408 crossref_primary_10_1109_ACCESS_2023_3269848 crossref_primary_10_1007_s10462_025_11166_1 crossref_primary_10_1109_MWC_003_2200469 crossref_primary_10_1109_TIFS_2024_3423428 crossref_primary_10_1007_s10462_025_11317_4 crossref_primary_10_1109_JSAC_2025_3559152 crossref_primary_10_1109_TWC_2024_3478232 crossref_primary_10_1109_JSAC_2025_3574624 crossref_primary_10_1109_TWC_2023_3314930 crossref_primary_10_1109_COMST_2023_3333342 crossref_primary_10_1109_TWC_2024_3392608 crossref_primary_10_1016_j_comnet_2025_111270 crossref_primary_10_1007_s10922_025_09927_y crossref_primary_10_1109_MCOM_004_2200819 crossref_primary_10_1109_JSAC_2025_3574587 crossref_primary_10_1109_TCOMM_2024_3416898 crossref_primary_10_1109_TCCN_2024_3384492 crossref_primary_10_1109_TWC_2023_3306342 crossref_primary_10_1016_j_comcom_2022_09_005 crossref_primary_10_1016_j_engappai_2024_108677 crossref_primary_10_1109_TWC_2024_3512663 crossref_primary_10_1109_ACCESS_2024_3360003 crossref_primary_10_1109_JIOT_2025_3527016 crossref_primary_10_1016_j_trc_2025_105164 crossref_primary_10_1109_COMST_2022_3199901 crossref_primary_10_1109_LCOMM_2025_3587319 crossref_primary_10_1049_cmu2_12557 crossref_primary_10_1109_MBITS_2023_3322667 crossref_primary_10_1109_ACCESS_2024_3381967
Cites_doi	10.18653/v1/2020.acl-main.685 10.1109/JSAIT.2020.2987203 10.1109/ACSSC.2017.8335670 10.1109/COMST.2018.2888904 10.1007/s41745-020-00165-6 10.1007/BF00735341 10.1109/JSAC.2019.2933891 10.1109/TCCN.2018.2872596 10.1109/MCOM.001.2000394 10.1109/PIMRC.2019.8904190 10.1109/SPAWC.2018.8445920 10.1162/neco.1997.9.8.1735 10.1007/BF00992696 10.1109/JSAC.2020.3036955 10.1145/375735.376455 10.1038/nature14236 10.1139/juvs-2018-0009 10.1109/LCOMM.2018.2877316 10.1109/TIT.2019.2953750 10.1177/10597123030111003 10.1103/PhysRev.36.823 10.1109/JSTSP.2017.2788405
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/JSAC.2021.3087248
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-0008
EndPage	2603
ExternalDocumentID	10_1109_JSAC_2021_3087248 9466501
Genre	orig-research
GrantInformation_xml	– fundername: U.K. Engineering and Physical Sciences Research Council (EPSRC) grantid: EP/T023600/1 funderid: 10.13039/501100000266 – fundername: European Research Council (ERC) Starting Grant BEACON grantid: 677854 funderid: 10.13039/501100000781
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 41~ 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IBMZZ ICLAB IES IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 VH1 AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c293t-a84caba6f1610e09df1ca15a7b5dd67c318c11b5c793b377be1866972a69f07e3
IEDL.DBID	RIE
ISICitedReferencesCount	72
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000673624000024&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0733-8716
IngestDate	Mon Jun 30 10:20:28 EDT 2025 Tue Nov 18 21:25:27 EST 2025 Sat Nov 29 03:23:03 EST 2025 Wed Aug 27 02:40:51 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c293t-a84caba6f1610e09df1ca15a7b5dd67c318c11b5c793b377be1866972a69f07e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-2716-5211
PQID	2552160392
PQPubID	85481
PageCount	14
ParticipantIDs	crossref_primary_10_1109_JSAC_2021_3087248 crossref_citationtrail_10_1109_JSAC_2021_3087248 proquest_journals_2552160392 ieee_primary_9466501
PublicationCentury	2000
PublicationDate	2021-08-01
PublicationDateYYYYMMDD	2021-08-01
PublicationDate_xml	– month: 08 year: 2021 text: 2021-08-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE journal on selected areas in communications
PublicationTitleAbbrev	J-SAC
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref34 ref15 ref14 ref31 ref30 wang (ref37) 2020 sukhbaatar (ref35) 2016 havrylov (ref36) 2017 xie (ref9) 2020 jaques (ref20) 2018 ref32 strinati (ref10) 2020 ref17 tomasello (ref3) 2010 silver (ref42) 2014 jiang (ref19) 2018 kingma (ref45) 2014 lowe (ref38) 2017; 30 foerster (ref18) 2016 ref46 ref23 ref26 bourtsoulatze (ref11) 2018 ref25 lazaridou (ref24) 2016 konda (ref33) 2000; 12 das (ref21) 2019 ref41 ref22 ref44 ref43 shannon (ref2) 1949 ref28 lillicrap (ref27) 2015 ref29 ref7 roig (ref1) 2020 ref6 peng (ref39) 2017 ref5 weng (ref12) 2020 ref40 ackley (ref4) 1994 kountouris (ref8) 2020 lanctot (ref16) 2017
References_xml	– year: 2016 ident: ref24 article-title: Multi-agent cooperation and the emergence of (Natural) language publication-title: arXiv 1612 07182 – ident: ref25 doi: 10.18653/v1/2020.acl-main.685 – year: 2020 ident: ref9 article-title: Deep learning enabled semantic communication systems publication-title: arXiv 2006 10685 – ident: ref31 doi: 10.1109/JSAIT.2020.2987203 – start-page: 40 year: 1994 ident: ref4 article-title: Altruism in the evolution of communication publication-title: Proc 4th Int Workshop Synth Simul Living Syst (Artificial Life IV) – ident: ref29 doi: 10.1109/ACSSC.2017.8335670 – year: 2017 ident: ref16 article-title: A unified game-theoretic approach to multiagent reinforcement learning publication-title: arXiv 1711 00832 – start-page: 387 year: 2014 ident: ref42 article-title: Deterministic policy gradient algorithms publication-title: Proc Int Conf Mach Learn – year: 2020 ident: ref37 article-title: R-MADDPG for partially observable environments and limited communication publication-title: arXiv 2002 06684 – year: 1949 ident: ref2 publication-title: The Mathematical Theory of Communication – volume: 30 start-page: 6379 year: 2017 ident: ref38 article-title: Multi-agent actor-critic for mixed cooperative-competitive environments publication-title: Proc Adv Neural Inf Process Syst – year: 2020 ident: ref12 article-title: Semantic communications for speech signals publication-title: arXiv 2012 05369 – ident: ref22 doi: 10.1109/COMST.2018.2888904 – start-page: 1 year: 2020 ident: ref1 article-title: Remote reinforcement learning over a noisy channel publication-title: Proc IEEE Globecom – ident: ref7 doi: 10.1007/s41745-020-00165-6 – year: 2017 ident: ref39 article-title: Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games publication-title: arXiv 1703 10069 – ident: ref17 doi: 10.1007/BF00735341 – start-page: 7265 year: 2018 ident: ref19 article-title: Learning attentional communication for multi-agent cooperation publication-title: Proc 32nd Int Conf Neural Inf Process Syst – year: 2014 ident: ref45 article-title: Adam: A method for stochastic optimization publication-title: arXiv 1412 6980 – ident: ref32 doi: 10.1109/JSAC.2019.2933891 – year: 2017 ident: ref36 article-title: Emergence of language with multi-agent games: Learning to communicate with sequences of symbols publication-title: arXiv 1705 11192 – year: 2010 ident: ref3 publication-title: Origins of Human Communication – start-page: 1538 year: 2019 ident: ref21 article-title: TarMAC: Targeted multi-agent communication publication-title: Proc 36th Int Conf Mach Learn – year: 2020 ident: ref8 article-title: Semantics-empowered communication for networked intelligent systems publication-title: arXiv 2007 11579 – ident: ref6 doi: 10.1109/TCCN.2018.2872596 – ident: ref15 doi: 10.1109/MCOM.001.2000394 – year: 2016 ident: ref18 article-title: Learning to communicate with deep multi-agent reinforcement learning publication-title: arXiv 1605 06676 – ident: ref40 doi: 10.1109/PIMRC.2019.8904190 – volume: 12 start-page: 1008 year: 2000 ident: ref33 article-title: Actor-critic algorithms publication-title: Proc Adv Neural Inf Process Syst – ident: ref30 doi: 10.1109/SPAWC.2018.8445920 – ident: ref46 doi: 10.1162/neco.1997.9.8.1735 – ident: ref44 doi: 10.1007/BF00992696 – start-page: 2252 year: 2016 ident: ref35 article-title: Learning multiagent communication with backpropagation publication-title: Proc 30th Int Conf Neural Inf Syst (NIPS) – year: 2018 ident: ref11 article-title: Deep joint source-channel coding for wireless image transmission publication-title: arXiv 1809 01733 – ident: ref14 doi: 10.1109/JSAC.2020.3036955 – ident: ref5 doi: 10.1145/375735.376455 – year: 2015 ident: ref27 article-title: Continuous control with deep reinforcement learning publication-title: arXiv 1509 02971 – year: 2020 ident: ref10 article-title: 6G networks: Beyond Shannon towards semantic and goal-oriented communications publication-title: arXiv 2011 14844 – year: 2018 ident: ref20 article-title: Social influence as intrinsic motivation for multi-agent deep reinforcement learning publication-title: arXiv 1810 08647 – ident: ref26 doi: 10.1038/nature14236 – ident: ref23 doi: 10.1139/juvs-2018-0009 – ident: ref41 doi: 10.1109/LCOMM.2018.2877316 – ident: ref13 doi: 10.1109/TIT.2019.2953750 – ident: ref34 doi: 10.1177/10597123030111003 – ident: ref43 doi: 10.1103/PhysRev.36.823 – ident: ref28 doi: 10.1109/JSTSP.2017.2788405
SSID	ssj0014482
Score	2.643482
Snippet	We propose a novel formulation of the "effectiveness problem" in communications, put forth by Shannon and Weaver in their seminal work " The Mathematical... We propose a novel formulation of the “effectiveness problem” in communications, put forth by Shannon and Weaver in their seminal work “ The Mathematical...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	2590
SubjectTerms	Channel coding Channels Communication channels Communications systems Deep learning Drone vehicles error correction coding joint source-channel coding Learning to communicate Markov processes Modulation multi-agent systems Multiagent systems Noise measurement Protocols Reagents Reinforcement learning reinforcement learning (RL) Semantics Wireless communication
Title	Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning Over Noisy Channels
URI	https://ieeexplore.ieee.org/document/9466501 https://www.proquest.com/docview/2552160392
Volume	39
WOSCitedRecordID	wos000673624000024&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0008 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014482 issn: 0733-8716 databaseCode: RIE dateStart: 19830101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61eNCDrypWq-TgSUzNPrPrrRSLFKniA3pbsnlIQXal3Qoe_edmstu1RRG87SEJgW8nM5PJ9w1CZymIqGsZEk-Gmvi-q0kcBZSkWvtMssj3lZXMv2WjUTQex_cNdFFzYZRS9vGZ6sKnreXLXMzhquwStNADIGutMRaWXK26YmDSDFsxYJ5HIAmoKpgOjS-Hj72-yQRdpwvydy60-lnyQbapyo-T2LqXwfb_NraDtqowEvdK3HdRQ2V7aHNJXLCFPkthYnOa4RUWyOwK9_Awn2QFrsRVXzDP5OogPFg82sImqsWWpkt6QMPCD8qKrQp7r_i9xJ2xCTzKJ7MPDIyFzPjcffQ8uH7q35Cq4QIRxusXhEe-4CkPtQkDqaKx1I7gTsBZGkgZMmHsXzhOGghj1KnHWKpALi9mLg9jTZnyDlAzyzN1iLAMXK0iETnKZKCMpiA7yOHOi0nP15y2EV1AkIhKjRyaYrwmNiuhcQKoJYBaUqHWRuf1lLdSiuOvwS2AqR5YIdRGnQXOSWWss8RkVS50247do99nHaMNWLt899dBzWI6VydoXbwXk9n01P6HXwmY21k
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5EBfXgW6xWzcGTGM0-s-utFEvVWsUHeFuyeUhBtmKr4NF_bia7rRVF8LaHSXbh28xkMvm-AdjPUUTdqJgGKjY0DH1D0yRiNDcm5IonYaidZH6Hd7vJw0N6PQWHYy6M1tpdPtNH-Ohq-aovX_Go7Bi10CMka81EdlZWsrXGNQObaLiaAQ8CimlAVcP0WHp8ftto2lzQ945QAM_HZj8TUci1Vfnhi12AaS3979OWYbHaSJJGifwKTOliFRYm5AXX4KOUJrb-jHzjgQxOSIOc93vFkFTyqo9EFOq7EWmNrm0Ru68ljqhLG0jEIjfaya1Kd7L4NcWVXRWk2-8N3glyFgobddfhvnV612zTquUClTbuD6lIQilyERu7EWSapcp4UniR4HmkVMyl9QDS8_JI2mWdB5znGgXzUu6LODWM62ADpot-oTeBqMg3OpGJp20OylmOwoMCT724CkIjWA3YCIJMVnrk2BbjKXN5CUszRC1D1LIKtRocjIc8l2IcfxmvIUxjwwqhGtRHOGfVch1kNq_ysd926m_9PmoP5tp3l52sc9a92IZ5fE95C7AO08OXV70Ds_Jt2Bu87Lp_8hOX4d6g
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Effective+Communications%3A+A+Joint+Learning+and+Communication+Framework+for+Multi-Agent+Reinforcement+Learning+Over+Noisy+Channels&rft.jtitle=IEEE+journal+on+selected+areas+in+communications&rft.au=Tze-Yang%2C+Tung&rft.au=Kobus%2C+Szymon&rft.au=Joan+Pujol+Roig&rft.au=Gunduz%2C+Deniz&rft.date=2021-08-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0733-8716&rft.eissn=1558-0008&rft.volume=39&rft.issue=8&rft.spage=2590&rft_id=info:doi/10.1109%2FJSAC.2021.3087248&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0733-8716&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0733-8716&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0733-8716&client=summon