{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:28:28Z","timestamp":1730255308377,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197199","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"4434-4440","source":"Crossref","is-referenced-by-count":2,"title":["Learning Navigation Costs from Demonstration in Partially Observable Environments"],"prefix":"10.1109","author":[{"given":"Tianyu","family":"Wang","sequence":"first","affiliation":[]},{"given":"Vikas","family":"Dhiman","sequence":"additional","affiliation":[]},{"given":"Nikolay","family":"Atanasov","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759328"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref15","first-page":"4694","article-title":"QMDP-Net: Deep learning for planning under partial observability","author":"karkus","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.039"},{"key":"ref17","first-page":"174","article-title":"Optimal control of markov processes with incomplete state information","volume":"10","author":"strm","year":"0","journal-title":"Journal of Mathematical Analysis and Applications"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2008.IV.009"},{"key":"ref19","article-title":"Memory augmented control networks","author":"khan","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref3","first-page":"295","article-title":"Apprenticeship learning using inverse&#x00B4; reinforcement learning and gradient methods","author":"neu","year":"2007","journal-title":"Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence"},{"key":"ref6","first-page":"2154","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref5","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence"},{"key":"ref8","first-page":"767774","article-title":"ARA*: Anytime A* with Provable Bounds on Sub-Optimality","author":"likhachev","year":"2004","journal-title":"Advances in neural information processing systems"},{"article-title":"Path integral networks: End-to-end differentiable optimal control","year":"2017","author":"okada","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"article-title":"Rapidly-exploring random trees: A new tool for path planning","year":"1998","author":"lavalle","key":"ref9"},{"key":"ref1","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"ref20","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume":"7","author":"ramachandran","year":"2007","journal-title":"IJCAI"},{"journal-title":"Probabilistic Robotics","year":"2005","author":"thrun","key":"ref22"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref21"},{"key":"ref24","volume":"3","author":"shor","year":"2012","journal-title":"Minimization Methods for Non-Differentiable Functions"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9321-0"},{"key":"ref26","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref25","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"NIPS-W"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197199.pdf?arnumber=9197199","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:22:19Z","timestamp":1656375739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197199\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197199","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}