{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:01:41Z","timestamp":1766138501558,"version":"3.37.3"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,21]]},"DOI":"10.1109\/cog57401.2023.10333236","type":"proceedings-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T18:48:21Z","timestamp":1701715701000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation"],"prefix":"10.1109","author":[{"given":"Ayesha Siddika","family":"Nipu","sequence":"first","affiliation":[{"name":"Missouri State University,Department of Computer Science,Springfield,U.S."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siming","family":"Liu","sequence":"additional","affiliation":[{"name":"Missouri State University,Department of Computer Science,Springfield,U.S."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony","family":"Harris","sequence":"additional","affiliation":[{"name":"Missouri State University,Department of Computer Science,Springfield,U.S."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref13"},{"key":"ref12","article-title":"Actor-critic algorithms","volume":"12","author":"konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319733"},{"article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","year":"2021","author":"yu","key":"ref14"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref30","article-title":"The StarCraft multi-agent challenge","volume":"abs 1902 4043","author":"samvelyan","year":"2019","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933454"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2769104"},{"key":"ref2","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":"ref1","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":"ref17","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","article-title":"Transfer learning using kolmogorov complexity: Basic theory and empirical evaluations","volume":"20","author":"mahmud","year":"2007","journal-title":"Advances in neural information processing systems"},{"article-title":"Net2net: Accelerating learning via knowledge transfer","year":"2015","author":"chen","key":"ref19"},{"key":"ref18","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"yosinski","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3071162"},{"article-title":"Starcraft ii: A new challenge for reinforcement learning","year":"2017","author":"vinyals","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893711"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICBASE53849.2021.00107"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783295"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00199"},{"article-title":"Multi-agent Actor-Critic for mixed cooperative-competitive environments","year":"2017","author":"lowe","key":"ref28"},{"article-title":"Multiagent bidirectionally-coordinated nets: emergence of human-level coordination in learning to play StarCraft combat games","year":"2017","author":"peng","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7471613"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14540"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1126\/science.aam6960","article-title":"Deepstack: Expert-level artificial intelligence in heads-up no-limit poker","volume":"356","author":"morav?\u00edk","year":"2017","journal-title":"Science"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/YAC.2016.7804906"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3032227"}],"event":{"name":"2023 IEEE Conference on Games (CoG)","start":{"date-parts":[[2023,8,21]]},"location":"Boston, MA, USA","end":{"date-parts":[[2023,8,24]]}},"container-title":["2023 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10333091\/10333129\/10333236.pdf?arnumber=10333236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T22:25:58Z","timestamp":1702419958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10333236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cog57401.2023.10333236","relation":{},"subject":[],"published":{"date-parts":[[2023,8,21]]}}}