{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:31:17Z","timestamp":1770845477099,"version":"3.50.1"},"reference-count":36,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342495","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"5236-5241","source":"Crossref","is-referenced-by-count":0,"title":["Categorical Policies: Multimodal Policy Learning and Exploration in Continuous Control"],"prefix":"10.1109","author":[{"given":"S M Mazharul","family":"Islam","sequence":"first","affiliation":[{"name":"University of Texas at Arlington,Department of Computer Science and Engineering,TX,USA,76019"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manfred","family":"Huber","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington,Department of Computer Science and Engineering,TX,USA,76019"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref2","first-page":"24639","article-title":"Video pretraining (vpt): Learning to act by watching unlabeled online videos","volume":"35","author":"Baker","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref4","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2020"},{"key":"ref5","article-title":"Learning awareness models","author":"Amos","year":"2018"},{"key":"ref6","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"International conference on machine learning","author":"Hafner"},{"key":"ref7","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Actor-critic algorithms","volume":"12","author":"Konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref10","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"Silver"},{"key":"ref11","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019"},{"key":"ref12","article-title":"Deepmind control suite","author":"Tassa","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","article-title":"Mastering diverse domains through world models, 2023","author":"Hafner","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref17","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref18","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"Maddison","year":"2016"},{"key":"ref19","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31635-3_22"},{"key":"ref21","article-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018"},{"key":"ref22","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":"ref23","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref25","first-page":"1430","article-title":"Goal-conditioned reinforcement learning with imagined subgoals","volume-title":"International conference on machine learning","author":"Chane-Sane"},{"key":"ref26","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","volume":"22","author":"Konidaris","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"8624","article-title":"Learning robot skills with temporal variational inference","volume-title":"International Conference on Machine Learning","author":"Shankar"},{"key":"ref28","article-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2018"},{"key":"ref29","article-title":"Variational curriculum reinforcement learning for unsupervised discovery of skills","author":"Kim","year":"2023"},{"key":"ref30","first-page":"24379","article-title":"Discovering and achieving goals via world models","volume":"34","author":"Mendonca","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Variational option discovery algorithms","author":"Achiam","year":"2018"},{"issue":"Aug","key":"ref32","first-page":"1063","article-title":"Reinforcement learning with factored states and actions","volume":"5","author":"Sallans","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6059"},{"key":"ref35","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","volume":"28","author":"Watter","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"}],"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\/11342495.pdf?arnumber=11342495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:51Z","timestamp":1770843051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342495\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342495","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}