{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T05:17:44Z","timestamp":1740719864430,"version":"3.38.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"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":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10886519","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"8825-8831","source":"Crossref","is-referenced-by-count":0,"title":["Generalized Maximum Entropy Differential Dynamic Programming"],"prefix":"10.1109","author":[{"given":"Yuichiro","family":"Aoyama","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology,School of Aerospace Engineering,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelos A.","family":"Theodorou","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,School of Aerospace Engineering,Atlanta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/bf01016429"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108963558"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0503807102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00032-008-0087-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1103\/physreva.67.051402"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1103\/physrevlett.100.055003"},{"volume-title":"Pattern Recognition and Machine Learning","year":"2006","author":"Bishop","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1103\/physrevlett.75.3589"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2398","DOI":"10.1103\/PhysRevE.60.2398","article-title":"Nonextensive foundation of l\u00e9vy distributions","volume":"60","author":"Prato","year":"1999","journal-title":"Phys. Rev. E"},{"issue":"8","key":"ref10","doi-asserted-by":"crossref","first-page":"1450","DOI":"10.1016\/j.jvcir.2013.10.005","article-title":"q-gaussian mixture models for image and video semantic indexing","volume":"24","author":"Inoue","year":"2013","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"ref11","first-page":"1059","article-title":"q-gaussian based smoothed functional algorithms for stochastic optimization","volume-title":"2012 IEEE International Symposium on Information Theory Proceedings","author":"Ghoshdastidar"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-010-0686-8"},{"key":"ref13","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Haarnoja"},{"key":"ref14","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","volume-title":"Ph.D. dissertation","author":"Ziebart","year":"2010"},{"key":"ref15","first-page":"1714","article-title":"Information theoretic mpc for model-based reinforcement learning","volume-title":"2017 IEEE International Conference on Robotics and Automation (ICRA)","author":"Williams"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2021.XVII.073","article-title":"Variational inference mpc using tsallis divergence","author":"Wang","year":"2021","journal-title":"Robotics Science and Systems (RSS)"},{"article-title":"Effective exploration for deep reinforcement learning via bootstrapped q-ensembles under tsallis entropy regularization","year":"2018","author":"Chen","key":"ref17"},{"article-title":"Tsallis reinforcement learning: A unified framework for maximum entropy reinforcement learning","year":"2019","author":"Lee","key":"ref18"},{"article-title":"Enforcing kl regularization in general tsallis entropy reinforcement learning via advantage learning","year":"2022","author":"Zhu","key":"ref19"},{"volume-title":"Differential dynamic programming","year":"1970","author":"Jacobson","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9812228"},{"issue":"6","key":"ref22","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1109\/9.86943","article-title":"Convergence in unconstrained discrete-time differential dynamic programming","volume":"36","author":"Liao","year":"1991","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"12","key":"ref23","doi-asserted-by":"crossref","first-page":"4805","DOI":"10.1109\/TIT.2007.909173","article-title":"Generalized box-m\u00dcller method for generating q-gaussian random deviates","volume":"53","author":"Thistleton","year":"2007","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"ref24","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.physa.2006.01.028","article-title":"Poincar\u00e9\u2019s observation and the origin of tsallis generalized canonical distributions","volume":"365","author":"Vignat","year":"2006","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8113\/40\/45\/f02"},{"issue":"1","key":"ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2307\/2331554","article-title":"The probable error of a mean","volume":"6","year":"1908","journal-title":"Biometrika"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2628434"},{"article-title":"Modelling and control of quadcopter","volume-title":"Independent research project in applied mathematics","author":"Luukkonen","key":"ref28"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","start":{"date-parts":[[2024,12,16]]},"location":"Milan, Italy","end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10886519.pdf?arnumber=10886519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:25:30Z","timestamp":1740641130000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886519\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10886519","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}