{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:38:21Z","timestamp":1770845901346,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342829","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"4181-4188","source":"Crossref","is-referenced-by-count":0,"title":["Imitation Learning with Process Adversarial Diffusion"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Qi","sequence":"first","affiliation":[{"name":"Nanjing University,School of Management and Engineering,Department of Control Science and Intelligence Engineering,Nanjing,China,210093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiqiao","family":"Fu","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Management and Engineering,Department of Control Science and Intelligence Engineering,Nanjing,China,210093"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing University,Center for Advanced Control and Smart Operations (CACSO),Suzhou,China,215163"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Management and Engineering,Department of Control Science and Intelligence Engineering,Nanjing,China,210093"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/328"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3345539"},{"key":"ref5","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"International Conference on Machine Learning","volume":"3","author":"Ng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref8","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"AAAI Conference on Artificial Intelligence","volume":"8","author":"Ziebart"},{"key":"ref9","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"4028","article-title":"Iq-learn: Inverse soft-q learning for imitation","volume":"34","author":"Garg","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref11","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"International Conference on Artificial Intelligence and Statistics","volume":"15","author":"Ross"},{"key":"ref12","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"ref16","article-title":"Towards principled methods for training generative adversarial networks","volume-title":"International Conference on Learning Representations","author":"Arjovsky"},{"key":"ref17","article-title":"Unrolled generative adversarial networks","author":"Metz","year":"2016"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Neural Information Processing Systems"},{"key":"ref19","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016"},{"key":"ref20","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref21","first-page":"27953","article-title":"Flexible diffusion modeling of long videos","volume":"35","author":"Harvey","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref22","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"International Conference on Learning Representations","author":"Kong"},{"key":"ref23","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29470"},{"key":"ref25","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","volume-title":"International Conference on Machine Learning","author":"Hazan"},{"key":"ref26","first-page":"60048","article-title":"Ess-InfoGAIL: Semi-supervised imitation learning from imbalanced demonstrations","volume":"36","author":"Fu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref28","first-page":"64896","article-title":"Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning","volume":"36","author":"He","year":"2023","journal-title":"Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref30","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"International Conference on Machine Learning","author":"Janner"},{"key":"ref31","article-title":"Is conditional generative modeling all you need for decision making?","volume-title":"International Conference on Learning Representations","author":"Ajay"},{"key":"ref32","article-title":"Adapt Diffuser: Diffusion Models as Adaptive Self-evolving Planners","volume-title":"International Conference on Machine Learning","author":"Liang"},{"key":"ref33","article-title":"MADiff: Offline multi-agent learning with diffusion models","author":"Zhu","year":"2023"},{"key":"ref34","article-title":"Efficient exploration via state marginal matching","author":"Lee","year":"2019"},{"key":"ref35","article-title":"Imitating human behaviour with diffusion models","volume-title":"International Conference on Learning Representations","author":"Pearce"},{"key":"ref36","first-page":"10357","article-title":"A coupled flow approach to imitation learning","volume-title":"International Conference on Machine Learning","volume":"202","author":"Freund"},{"key":"ref37","article-title":"Imitation learning via off-Policy distribution matching","volume-title":"International Conference on Learning Representations","author":"Kostrikov"},{"key":"ref38","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342829.pdf?arnumber=11342829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:52:01Z","timestamp":1770843121000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342829","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}