{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:11:38Z","timestamp":1778184698925,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":[[2025,12,3]]},"DOI":"10.1109\/icmla66185.2025.00094","type":"proceedings-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T19:54:58Z","timestamp":1775591698000},"page":"655-662","source":"Crossref","is-referenced-by-count":0,"title":["Mamba World Model for RL: Enhancing Long-term Memory in Model-based Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Mingcong","family":"Cao","sequence":"first","affiliation":[{"name":"University of Wisconsin–Madison,Dept. of ECE,Madison,USA"}]},{"given":"Yucheng","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Wisconsin–Madison,Dept. of ECE & CS,Madison,USA"}]},{"given":"Suat","family":"Gumussoy","sequence":"additional","affiliation":[{"name":"Siemens Corporate Technology,Princeton,USA"}]},{"given":"Umit Y.","family":"Ogras","sequence":"additional","affiliation":[{"name":"University of Wisconsin–Madison,Dept. of ECE,Madison,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint arXiv:1312.5602"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref3","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv preprint arXiv:1912.06680"},{"key":"ref4","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref5","article-title":"PD-MORL: Preference-driven multi-objective reinforcement learning algorithm","volume-title":"The Eleventh International Conference on Learning Representations","author":"Basaklar"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3762655"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26224"},{"key":"ref9","article-title":"Recurrent world models facilitate policy evolution","volume":"31","author":"Ha","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Mastering atari with discrete world models","volume-title":"International Conference on Learning Representations","author":"Hafner"},{"key":"ref11","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv preprint arXiv:2301.04104"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref13","article-title":"Model based reinforcement learning for atari","volume-title":"International Conference on Learning Representations","author":"Kaiser"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3043083"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1182"},{"key":"ref19","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv:2312.00752"},{"key":"ref20","article-title":"Drama: Mamba-enabled model-based reinforcement learning is sample and parameter efficient","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2410.08893"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref22","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"International conference on machine learning","author":"Hafner"},{"key":"ref23","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv preprint arXiv:1912.01603"},{"key":"ref24","article-title":"Transformers are sample-efficient world models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Micheli"},{"key":"ref25","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Transformer-based world models are happy with 100k interactions","volume-title":"The Eleventh International Conference on Learning Representations","author":"Robine"},{"key":"ref27","first-page":"1474","article-title":"Hippo: Recurrent memory with optimal polynomial projections","volume":"33","author":"Gu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"International Conference on Learning Representations","author":"Gu"},{"key":"ref29","article-title":"Simplified state space layers for sequence modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Smith"},{"key":"ref30","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Forty-first International Conference on Machine Learning","author":"Dao"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3209"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref34","article-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury","year":"2018"},{"issue":"9","key":"ref35","article-title":"Compiling machine learning programs via high-level tracing","volume":"4","author":"Frostig","year":"2018","journal-title":"Systems for Machine Learning"},{"key":"ref36","article-title":"SheepRL","author":"Angioni","year":"2023"}],"event":{"name":"2025 International Conference on Machine Learning and Applications (ICMLA)","location":"Boca Raton, FL, USA","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Machine Learning and Applications (ICMLA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11471302\/11471304\/11471345.pdf?arnumber=11471345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:50:53Z","timestamp":1778183453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icmla66185.2025.00094","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}