{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T02:35:14Z","timestamp":1780626914810,"version":"3.54.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Center for Applied Research in Artificial Intelligence"},{"DOI":"10.13039\/501100003626","name":"Defense Acquisition Program Administration (DAPA) and Agency for Defense Development","doi-asserted-by":"publisher","award":["UD190031RD"],"award-info":[{"award-number":["UD190031RD"]}],"id":[{"id":"10.13039\/501100003626","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3266652","type":"journal-article","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T17:33:35Z","timestamp":1681320815000},"page":"37854-37868","source":"Crossref","is-referenced-by-count":4,"title":["The StarCraft Multi-Agent Exploration Challenges: Learning Multi-Stage Tasks and Environmental Factors Without Precise Reward Functions"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5082-7223","authenticated-orcid":false,"given":"Mingyu","family":"Kim","sequence":"first","affiliation":[{"name":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihwan","family":"Oh","sequence":"additional","affiliation":[{"name":"Department of Economics and Law, Korea Military Academy, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongsik","family":"Lee","sequence":"additional","affiliation":[{"name":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2155-6556","authenticated-orcid":false,"given":"Joonkee","family":"Kim","sequence":"additional","affiliation":[{"name":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seonghwan","family":"Kim","sequence":"additional","affiliation":[{"name":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Chong","sequence":"additional","affiliation":[{"name":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6675-5113","authenticated-orcid":false,"given":"Seyoung","family":"Yun","sequence":"additional","affiliation":[{"name":"Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"6860","article-title":"Coach-player multi-agent reinforcement learning for dynamic team composition","author":"liu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","article-title":"Decomposed soft actor-critic method for cooperative multi-agent reinforcement learning","author":"pu","year":"2021","journal-title":"arXiv 2104 06655"},{"key":"ref12","first-page":"4596","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","author":"iqbal","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1142\/9789812777263_0020"},{"key":"ref15","first-page":"23049","article-title":"RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents","volume":"34","author":"qiu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref14","article-title":"DFAC framework: Factorizing the value function via quantile mixture for multi-agent distributional Q-learning","author":"sun","year":"2021","journal-title":"arXiv 2102 07936"},{"key":"ref36","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","author":"liu","year":"1993","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","article-title":"UPDeT: Universal multi-agent reinforcement learning via policy decoupling with transformers","author":"hu","year":"2021","journal-title":"arXiv 2101 08001"},{"key":"ref33","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"arXiv 2103 01955"},{"key":"ref10","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref17","first-page":"2661","article-title":"Zero-shot task generalization with multi-task deep reinforcement learning","author":"oh","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref16","first-page":"20347","article-title":"Disentangling sources of risk for distributional multi-agent reinforcement learning","author":"son","year":"2022","journal-title":"Proc 39th Int Conf Mach Learn"},{"key":"ref38","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"1","article-title":"Hierarchical reinforcement learning for zero-shot generalization with subtask dependencies","author":"sohn","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref18","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv 1708 04782"},{"key":"ref24","first-page":"1180","article-title":"Learning multi-stage tasks with one demonstration via self-replay","author":"palo","year":"2021","journal-title":"Proc 5th Annu Conf Robot Learn"},{"key":"ref23","first-page":"1","article-title":"‘Good robot! Now watch this!’: Repurposing reinforcement learning for task-to-task transfer","author":"hundt","year":"2021","journal-title":"Proc 5th Annu Conf Robot Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"ref25","article-title":"Collisional ionization in the X-ray spectrum of the ultracompact binary 4U 1626–67","author":"schulz","year":"2019","journal-title":"arXiv 1911 11684"},{"key":"ref20","article-title":"MazeBase: A sandbox for learning from games","author":"sukhbaatar","year":"2015","journal-title":"arXiv 1511 07401"},{"key":"ref22","article-title":"AVID: Learning multi-stage tasks via pixel-level translation of human videos","author":"smith","year":"2019","journal-title":"arXiv 1912 04443"},{"key":"ref21","first-page":"1","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"gupta","year":"2019","journal-title":"Proc Conf Robot Learn (CoRL)"},{"key":"ref28","article-title":"A game-theoretic model and best-response learning method for ad hoc coordination in multiagent systems","author":"albrecht","year":"2015","journal-title":"arXiv 1506 01170"},{"key":"ref27","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref29","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume":"34","author":"peng","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017","journal-title":"arXiv 1706 05296"},{"key":"ref7","article-title":"The StarCraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"arXiv 1902 04043"},{"key":"ref9","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Proc 1st Annu Conf Robot Learn"},{"key":"ref3","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"cobbe","year":"2019","journal-title":"arXiv 1912 01588"},{"key":"ref6","first-page":"1","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","author":"papoudakis","year":"2021","journal-title":"Proc 35th Conf Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/app10196900"},{"key":"ref40","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","author":"dabney","year":"2018","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10099458.pdf?arnumber=10099458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T18:58:19Z","timestamp":1683572299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10099458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3266652","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}