{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:06Z","timestamp":1763190786667,"version":"3.45.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227266","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Counterfactual Multi-agent Decision Transformer"],"prefix":"10.1109","author":[{"given":"Fanfan","family":"Zhao","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanquan","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wai Kin Victor","family":"Chan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"key":"ref2","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"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref3"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref4"},{"article-title":"Smacv2: An improved benchmark for multi-agent reinforcement learning","year":"2022","author":"Ellis","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref7","first-page":"2442","article-title":"Off-the-grid marl: Datasets and baselines for offline multi-agent reinforcement learning","volume-title":"Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems","author":"Formanek"},{"key":"ref8","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331237"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"International Conference on Learning Representations","author":"Jang","key":"ref12"},{"key":"ref13","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"},{"key":"ref14","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"27921","article-title":"Multi-game decision transformers","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1383-7"},{"article-title":"Flatland-rl: Multi-agent reinforcement learning on trains","year":"2020","author":"Mohanty","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref20","first-page":"17221","article-title":"Plan better amid conservatism: Offline multi-agent reinforcement learning with actor rectification","volume-title":"International Conference on Machine Learning","author":"Pan"},{"key":"ref21","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"International conference on machine learning","author":"Parisotto"},{"journal-title":"Advantage weighted regression: Simple and scalable off-policy reinforcement learning","year":"2020","author":"Peng","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"journal-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref24"},{"key":"ref25","first-page":"10199","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref26","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"article-title":"A generalist agent","year":"2022","author":"Reed","key":"ref27"},{"article-title":"The starcraft multi-agent challenge","year":"2019","author":"Samvelyan","key":"ref28"},{"article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","year":"2016","author":"Shalev-Shwartz","key":"ref29"},{"article-title":"Counterfactual conservative q learning for offline multi-agent reinforcement learning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Shao","key":"ref30"},{"key":"ref31","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Son"},{"key":"ref32","article-title":"Offline multi-agent reinforcement learning with knowledge distillation","volume-title":"Advances in Neural Information Processing Systems","author":"Tseng","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Offline multi-agent reinforcement learning with coupled value factorization","year":"2023","author":"Wang","key":"ref35"},{"key":"ref36","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume":"35","author":"Wen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","first-page":"10299","article-title":"Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning","volume":"34","author":"Yang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227266.pdf?arnumber=11227266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:09:33Z","timestamp":1763190573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227266","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}