{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T09:01:12Z","timestamp":1769850072601,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015539","name":"Australian Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,1]]},"DOI":"10.1109\/ssci47803.2020.9308391","type":"proceedings-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T23:12:38Z","timestamp":1609888358000},"page":"241-249","source":"Crossref","is-referenced-by-count":11,"title":["Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms"],"prefix":"10.1109","author":[{"given":"Aaron J.","family":"Snoswell","sequence":"first","affiliation":[]},{"given":"Surya P. N.","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Nan","family":"Ye","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630743"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/18.910572"},{"key":"ref12","author":"lafferty","year":"2001","journal-title":"Conditional Random Fields Probabilistic Models for Segmenting and Labeling Sequence Data"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1145\/2833157.2833162","article-title":"Numba: A LLVM-Based Python JIT Compiler","author":"lam","year":"2015","journal-title":"Proceedings of the 2nd Workshop on the LLVM Compiler Infrastructure in HPC"},{"key":"ref14","first-page":"278","article-title":"Policy Invariance under Reward Transformations: Theory and Application to Reward Shaping","volume":"1","author":"ng","year":"1999","journal-title":"16th International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.24.11.1127"},{"key":"ref16","first-page":"1073","volume":"36 10","author":"wulfmeier","year":"2017","journal-title":"Large-Scale Cost Function Learning for Path Planning Using Deep Inverse Reinforcement Learning"},{"key":"ref17","author":"ziebart","year":"2010","journal-title":"Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy"},{"key":"ref18","article-title":"Modeling Interaction via the Principle of Maximum Causal Entropy","author":"ziebart","year":"2010","journal-title":"27th International Conference on Machine Learning"},{"key":"ref19","first-page":"1433","article-title":"Maximum Entropy Inverse Reinforcement Learning","volume":"8","author":"ziebart","year":"2008","journal-title":"22nd AAAI Conference on Artificial Intelligence"},{"key":"ref4","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref3","first-page":"182","article-title":"Relative Entropy Inverse Reinforcement Learning","author":"boularias","year":"2011","journal-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics"},{"key":"ref6","author":"dua","year":"2017","journal-title":"UCI Machine Learning Repository"},{"key":"ref5","first-page":"691","article-title":"Inverse Reinforcement Learning in Partially Observable Environments","volume":"12","author":"choi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","author":"finn","year":"2016","journal-title":"A connection between generative adversarial networks inverse reinforcement learning and energy-based models"},{"key":"ref7","first-page":"49","article-title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","author":"finn","year":"2016","journal-title":"33rd International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094679"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref9","author":"fu","year":"2017","journal-title":"Learning robust rewards with adversarial inverse reinforcement learning"},{"key":"ref20","first-page":"1433","article-title":"Maximum Entropy Inverse Reinforcement Learning (manuscript updated)","volume":"8","author":"ziebart","year":"2010","journal-title":"22nd AAAI Conference on Artificial Intelligence"}],"event":{"name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Canberra, ACT, Australia","start":{"date-parts":[[2020,12,1]]},"end":{"date-parts":[[2020,12,4]]}},"container-title":["2020 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9308061\/9308107\/09308391.pdf?arnumber=9308391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:16:26Z","timestamp":1656602186000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9308391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,1]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ssci47803.2020.9308391","relation":{},"subject":[],"published":{"date-parts":[[2020,12,1]]}}}