{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:28:14Z","timestamp":1730204894165,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"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":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9993177","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"6824-6829","source":"Crossref","is-referenced-by-count":0,"title":["Sparsity Inducing System Representations for Policy Decompositions"],"prefix":"10.1109","author":[{"given":"Ashwin","family":"Khadke","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA,15213"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hartmut","family":"Geyer","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA,15213"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/humanoids47582.2021.9555796"},{"article-title":"Search methods for policy decompositions","year":"2022","author":"Khadke","key":"ref2"},{"key":"ref3","article-title":"Unsupervised state representation learning in atari","volume":"32","author":"Anand","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"A geometric perspective on optimal representations for reinforcement learning","volume":"32","author":"Bellemare","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"2170","article-title":"Deepmdp: Learning continuous latent space models for representation learning","volume-title":"International Conference on Machine Learning","author":"Gelada"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16880"},{"key":"ref7","article-title":"Nonlinear control of underactuated mechanical systems with application to robotics and aerospace vehicles","volume-title":"Ph.D. dissertation, Massachusetts Institute of Technology","author":"Olfati-Saber","year":"2001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570472"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/oca.854"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102568"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.657"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/00207170410001713448"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1983.1103170"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0150171"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.052"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.054"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref18"},{"issue":"2","key":"ref19","volume-title":"Dynamic programming and optimal control.","volume":"1","author":"Bertsekas","year":"1995"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2322116"},{"issue":"268","key":"ref21","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume-title":"Journal of Machine Learning Research","volume":"22","author":"Raffin","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0584-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/0911052"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","start":{"date-parts":[[2022,12,6]]},"location":"Cancun, Mexico","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09993177.pdf?arnumber=9993177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:08:02Z","timestamp":1706789282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9993177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9993177","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}