{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T20:59:52Z","timestamp":1774990792365,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"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":[[2019,9]]},"DOI":"10.1109\/allerton.2019.8919959","type":"proceedings-article","created":{"date-parts":[[2019,12,6]],"date-time":"2019-12-06T04:23:39Z","timestamp":1575606219000},"page":"824-831","source":"Crossref","is-referenced-by-count":2,"title":["Modeling and optimization of Human-Machine Interaction Processes via the Maximum Entropy Principle"],"prefix":"10.1109","author":[{"given":"Jiaxiao","family":"Zheng","sequence":"first","affiliation":[{"name":"The University of Texas at Austin,Department of Electrical and Computer Engineering,Austin,TX,78712"}]},{"given":"Gustavo de","family":"Veciana","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,Department of Electrical and Computer Engineering,Austin,TX,78712"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0963721410364008"},{"key":"ref11","article-title":"The use of transition entropy in partially observable markov decision processes","author":"melo","year":"2005"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1037\/h0045106"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139173933"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","article-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"puterman","year":"1994"},{"key":"ref16","first-page":"101","article-title":"Model-based reinforcement learning with an approximate, learned model","author":"sutton","year":"1996","journal-title":"Proceedings of the Ninth Yale Workshop on Adaptive and Learning Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.108.3.550"},{"key":"ref19","article-title":"Computational rationalization: The inverse equilibrium problem","author":"waugh","year":"2013","journal-title":"arXiv preprint arXiv 1308 3506"},{"key":"ref4","article-title":"Dynamic Programming and Optimal Control","author":"bertsekas","year":"2000","journal-title":"Athena Scientific"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-18324-9"},{"key":"ref6","article-title":"Mindwise: Why we misunderstand what others think, believe, feel, and want","author":"epley","year":"2015","journal-title":"Vintage"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref8","first-page":"262016","article-title":"Conversion path performance measures and reports","author":"hsiao","year":"0"},{"key":"ref7","first-page":"359","article-title":"Soft constraints in interactive behavior: The case of ignoring perfect knowledge in-the-world for imperfect knowledge in-the-head","volume":"28","author":"gray","year":"2004","journal-title":"Cognitive Science"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref1","first-page":"1638","article-title":"Taming the monster: A fast and simple algorithm for contextual bandits","author":"agarwal","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2019.8919959"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2234824"},{"key":"ref21","first-page":"207","article-title":"Maximum causal entropy correlated equilibria for markov games","author":"ziebart","year":"2011","journal-title":"The 10th International Conference on Autonomous Agents and Multiagent Systems"}],"event":{"name":"2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","location":"Monticello, IL, USA","start":{"date-parts":[[2019,9,24]]},"end":{"date-parts":[[2019,9,27]]}},"container-title":["2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8911248\/8919648\/08919959.pdf?arnumber=8919959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:51:39Z","timestamp":1774986699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8919959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/allerton.2019.8919959","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}