{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T16:33:58Z","timestamp":1729614838661,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561435","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"813-819","source":"Crossref","is-referenced-by-count":5,"title":["Solving Markov Decision Processes with Partial State Abstractions"],"prefix":"10.1109","author":[{"given":"Samer B.","family":"Nashed","sequence":"first","affiliation":[{"name":"University of Massachusetts,College of Information and Computer Sciences,Amherst,MA,USA"}]},{"given":"Justin","family":"Svegliato","sequence":"additional","affiliation":[{"name":"University of Massachusetts,College of Information and Computer Sciences,Amherst,MA,USA"}]},{"given":"Matteo","family":"Brucato","sequence":"additional","affiliation":[{"name":"University of Massachusetts,College of Information and Computer Sciences,Amherst,MA,USA"}]},{"given":"Connor","family":"Basich","sequence":"additional","affiliation":[{"name":"University of Massachusetts,College of Information and Computer Sciences,Amherst,MA,USA"}]},{"given":"Rod","family":"Grupen","sequence":"additional","affiliation":[{"name":"University of Massachusetts,College of Information and Computer Sciences,Amherst,MA,USA"}]},{"given":"Shlomo","family":"Zilberstein","sequence":"additional","affiliation":[{"name":"University of Massachusetts,College of Information and Computer Sciences,Amherst,MA,USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref38","first-page":"672","article-title":"Learning partial policies to speedup MDP tree search","author":"pinto","year":"2014","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v24i1.13636","article-title":"Planning under uncertainty using reduced models: Revisiting determinization","author":"pineda","year":"2014","journal-title":"The International Conference on Automated Planning & Scheduling"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1609\/icaps.v30i1.6671","article-title":"TLdR: Policy summarization for factored SSP problems using temporal abstractions","volume":"30","author":"sreedharan","year":"2020","journal-title":"International Conference on Automated Planning and Scheduling"},{"article-title":"Hierarchical solution of Markov decision processes using macro-actions","year":"2013","author":"hauskrecht","key":"ref31"},{"key":"ref30","first-page":"1175","article-title":"Lazy approximation for solving continuous finite-horizon MDPs","volume":"5","author":"li","year":"2005","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref37","first-page":"461","article-title":"Controlling deliberation in a Markov decision process-based agent","author":"alexander","year":"2008","journal-title":"International Joint Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref36","first-page":"467","article-title":"Soft labeling in stochastic shortest path problems","author":"pineda","year":"2019","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref35","first-page":"352","article-title":"FF-Replan: A baseline for probabilistic planning","volume":"7","author":"yoon","year":"2007","journal-title":"International Conference on Automated Planning and Scheduling"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967713"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461185"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(00)00047-3"},{"key":"ref11","article-title":"Agent-aware state estimation: Effective traffic light classification for autonomous vehicles","author":"parr","year":"2020","journal-title":"ICRA 2020 Workshop on Sensing Estimating and Understanding the Dynamic World"},{"key":"ref12","article-title":"Towards a unified theory of state abstraction for MDPs","author":"li","year":"2006","journal-title":"International Symposium on Artificial Intelligence and Mathematics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.14778\/2904483.2904489"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-1005-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-012-1077-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1000"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553478"},{"key":"ref18","first-page":"3342","article-title":"Approximate linear programming for constrained partially observable Markov decision processes","volume":"1","author":"poupart","year":"2015","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref19","first-page":"496","article-title":"Linear programming for large-scale Markov decision problems","author":"malek","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aan5074"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927528"},{"key":"ref3","article-title":"Mars 2020 science rover: Science goals and mission concept","volume":"45","author":"mustard","year":"2013","journal-title":"AAS\/Division for Planetary Sciences Meeting Abstracts #44"},{"key":"ref6","article-title":"Learning to optimize autonomy in competence-aware systems","author":"basich","year":"2020","journal-title":"The 10th International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803431"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967676"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i13.17386","article-title":"Ethically compliant sequential decision making","author":"svegliato","year":"2021","journal-title":"35th AAAI Conference on Artificial Intelligence"},{"key":"ref7","article-title":"Improving competence for reliable autonomy","author":"basich","year":"2021","journal-title":"ECAI Workshop on Agents and Robots for Reliable Engineered Autonomy"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363542"},{"key":"ref9","article-title":"Online decisionmaking for scalable autonomous systems","author":"wray","year":"2017","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20226"},{"key":"ref20","first-page":"1227","article-title":"Focused real-time dynamic programming for MDPs: Squeezing more out of a heuristic","author":"smith","year":"2006","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00376-4"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11036","article-title":"Fast SSP solvers using short-sighted labeling","author":"pineda","year":"2017","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.3.259"},{"article-title":"Model reduction techniques for computing approximately optimal solutions for Markov decision processes","year":"1997","author":"dean","key":"ref24"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00106-0"},{"key":"ref23","first-page":"162","article-title":"Metrics for finite Markov decision processes","volume":"4","author":"ferns","year":"2004","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11206-0_29"},{"article-title":"Online abstraction with MDP homomorphisms for deep learning","year":"2018","author":"biza","key":"ref26"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45622-8_15"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561435.pdf?arnumber=9561435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:48:29Z","timestamp":1673563709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561435","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}