{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:35:16Z","timestamp":1763202916741,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10649945","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Improving Zero-Shot Coordination with Diversely Rewarded Partner Agents"],"prefix":"10.1109","author":[{"given":"Peilin","family":"Wu","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology,Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation,Department of Computer Science and Engineering,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Yang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology,Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation,Department of Computer Science and Engineering,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Yang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology,Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation,Department of Computer Science and Engineering,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06004-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3895-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref5","first-page":"2105","article-title":"Learning representations that enable generalization in assistive tasks","volume-title":"Conference on Robot Learning","author":"He"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207872"},{"key":"ref7","article-title":"On the utility of learning about humans for human-ai coordination","volume":"32","author":"Carroll","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"4399","article-title":"\"Other-play\u201d for zero-shot coordination","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Hu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref10","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","first-page":"14502","article-title":"Collaborating with humans without human data","volume":"34","author":"Strouse","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"7204","article-title":"Trajectory diversity for zero-shot coordination","volume-title":"International conference on machine learning","author":"Lupu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25758"},{"article-title":"Learning zero-shot cooperation with humans, assuming humans are biased","volume-title":"International Conference on Learning Representations","author":"Yu","key":"ref14"},{"article-title":"Adaptive coordination in social embodied rearrangement","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Szot","key":"ref15"},{"key":"ref16","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"article-title":"Training agents using upside-down reinforcement learning","year":"2019","author":"Srivastava","key":"ref18"},{"article-title":"Reward-conditioned policies","year":"2019","author":"Kumar","key":"ref19"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref20"},{"article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"International Conference on Learning Representations","author":"Eysenbach","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7529"},{"article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Long","key":"ref24"},{"article-title":"Multi-agent collaboration via reward attribution decomposition","volume-title":"International Conference on Machine Learning","author":"Zhang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26388"},{"article-title":"Heterogeneous multi-agent zero-shot coordination by coevolution","year":"2022","author":"Xue","key":"ref27"},{"article-title":"Cooperative open-ended learning framework for zero-shot coordination","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Li","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/336"},{"article-title":"An efficient end-to-end training approach for zero-shot human-AI coordination","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Yan","key":"ref30"},{"article-title":"Reinforcement learning upside down: Don\u2019t predict rewards\u2013just map them to actions","year":"2019","author":"Schmidhuber","key":"ref31"},{"key":"ref32","first-page":"27042","article-title":"Online decision transformer","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Zheng"},{"key":"ref33","first-page":"12765","article-title":"Phasic self-imitative reduction for sparse-reward goal-conditioned reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Li"},{"article-title":"Rvs: What is essential for offline RL via supervised learning?","volume-title":"International Conference on Learning Representations","author":"Emmons","key":"ref34"},{"key":"ref35","first-page":"3902","article-title":"Adaptable agent populations via a generative model of policies","volume":"34","author":"Derek","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10649945.pdf?arnumber=10649945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:51:50Z","timestamp":1725943910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10649945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10649945","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}