{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:39:00Z","timestamp":1729643940983,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/iros.2017.8202240","type":"proceedings-article","created":{"date-parts":[[2017,12,14]],"date-time":"2017-12-14T22:12:59Z","timestamp":1513289579000},"page":"789-796","source":"Crossref","is-referenced-by-count":5,"title":["An information-theoretic on-line update principle for perception-action coupling"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Peng","sequence":"first","affiliation":[]},{"given":"Tim","family":"Genewein","sequence":"additional","affiliation":[]},{"given":"Felix","family":"Leibfried","sequence":"additional","affiliation":[]},{"given":"Daniel A.","family":"Braun","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref38","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS10)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1972.1054753"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1972.1054855"},{"key":"ref31","first-page":"142","article-title":"Coding Theorems for a Discrete Source With a Fidelity Criterion Institute of Radio Engineers","volume":"7","author":"shannon","year":"1959","journal-title":"International Convention Record"},{"key":"ref30","first-page":"205","article-title":"Information geometry and alternating minimization procedures","volume":"1","author":"csiszar","year":"1984","journal-title":"Stat Decis"},{"key":"ref37","article-title":"Online Algorithms and Stochastic Approximations","author":"bottou","year":"1998","journal-title":"Online Learning and Neural Networks"},{"key":"ref36","article-title":"Bounded Rational Decision-Making in Feedforward Neural Networks","author":"leibfried","year":"2016","journal-title":"Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"journal-title":"Information Theory and Network Coding","year":"2008","author":"yeung","key":"ref34"},{"key":"ref10","first-page":"156","article-title":"Truth and probability","author":"ramsey","year":"1931","journal-title":"The Foundations of Mathematics and Other Logical Essays"},{"key":"ref40","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Theory of Games and Economic Behavior","year":"1944","author":"von neumann","key":"ref11"},{"journal-title":"The Foundations of Statistics","year":"1954","author":"savage","key":"ref12"},{"journal-title":"Simple Heuristics that Make us Smart","year":"1999","author":"gigerenzer","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1257\/000282803322655392"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1037\/a0017187"},{"key":"ref16","first-page":"950","article-title":"Rationality and intelligence","author":"russell","year":"1995","journal-title":"Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence"},{"journal-title":"Artificial Intelligence A Modern Approach","year":"2002","author":"russell","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12086"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967366"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.95.200201"},{"journal-title":"Behavior-Based Robotics","year":"1998","author":"arkin","key":"ref4"},{"key":"ref27","first-page":"1369","article-title":"Linearly-solvable Markov decision problems","author":"todorov","year":"2006","journal-title":"Advances in neural information processing systems"},{"journal-title":"Action in Perception","year":"2004","author":"no\u00eb","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041360"},{"key":"ref29","article-title":"The information bottleneck method","author":"tishby","year":"1999","journal-title":"The 37th Annual Allerton Conference on Communication Control and Computing"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3585.001.0001","author":"pfeifer","year":"2006","journal-title":"How the Body Shapes the Way We Think A New View of Intelligence"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224787"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2014.2334912"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2015.00027"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224575"},{"journal-title":"Interactive perception Leveraging action in perception and perception in action","year":"0","author":"bogh","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/e16084662"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2012.0683"},{"key":"ref21","article-title":"Free energy and the generalized optimality equations for sequential decision making","author":"ortega","year":"2012","journal-title":"Workshop Conference"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2991\/agi.2010.10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907488"},{"key":"ref26","first-page":"3137","article-title":"A Generalized Path Integral Control Approach to Reinforcement Learning","volume":"11","author":"theodorou","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_24"},{"key":"ref25","first-page":"1607","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"Twenty-Fourth National Conference on Artificial Intelligence (AAAI-10)"}],"event":{"name":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2017,9,24]]},"location":"Vancouver, BC","end":{"date-parts":[[2017,9,28]]}},"container-title":["2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8119304\/8202121\/08202240.pdf?arnumber=8202240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T22:10:38Z","timestamp":1643148638000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8202240\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iros.2017.8202240","relation":{},"subject":[],"published":{"date-parts":[[2017,9]]}}}