{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T09:47:28Z","timestamp":1784454448983,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11245819","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"567-574","source":"Crossref","is-referenced-by-count":1,"title":["Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xiaocong","family":"Chen","sequence":"first","affiliation":[{"name":"Data 61, CSIRO,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Macquarie University,School of Computing,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Yu","sequence":"additional","affiliation":[{"name":"Adobe Research,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"Data 61, CSIRO,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref2","article-title":"Risk-averse offline reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Urp\u00ed"},{"key":"ref3","article-title":"Mildly conservative q-learning for offline reinforcement learning","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems","author":"Lyu"},{"key":"ref4","first-page":"19235","article-title":"Conservative offline distributional reinforcement learning","volume":"34","author":"Ma","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","article-title":"Imitating human behaviour with diffusion models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Pearce"},{"key":"ref6","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref7","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022"},{"key":"ref8","first-page":"958","article-title":"Improving robustness via risk averse distributional reinforcement learning","volume-title":"Learning for Dynamics and Control","author":"Singh","year":"2020"},{"key":"ref9","article-title":"Risk-averse model uncertainty for distributionally robust safe reinforcement learning","volume":"36","author":"Queeney","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref11","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International conference on machine learning","author":"Bellemare"},{"key":"ref12","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"International conference on machine learning","author":"Dabney"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref15","article-title":"Fully parameterized quantile function for distributional reinforcement learning","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2307\/1913738"},{"key":"ref17","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref18","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto"},{"key":"ref19","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"On fast sampling of diffusion probabilistic models","author":"Kong","year":"2021"},{"key":"ref23","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref24","article-title":"One risk to rule them all: A risk-sensitive perspective on model-based offline reinforcement learning","author":"Rigter","year":"2022"},{"key":"ref25","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning. PMLR","author":"Nichol"},{"key":"ref26","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref28","first-page":"1078","article-title":"Worst cases policy gradients","volume-title":"Proceedings of the Conference on Robot Learning, ser. Proceedings of Machine Learning Research","volume":"100","author":"Tang"},{"key":"ref29","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","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":"ref31","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"ref32","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11245819.pdf?arnumber=11245819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:19:41Z","timestamp":1766132381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245819","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}