{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T22:47:19Z","timestamp":1752101239252,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-1813490,IIS-1954782"],"award-info":[{"award-number":["IIS-1813490,IIS-1954782"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981612","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"11665-11670","source":"Crossref","is-referenced-by-count":3,"title":["Selecting the Partial State Abstractions of MDPs: A Metareasoning Approach with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Samer B.","family":"Nashed","sequence":"first","affiliation":[{"name":"University of Massachusetts,Amherst,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Svegliato","sequence":"additional","affiliation":[{"name":"University of California,Berkeley,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Bhatia","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Amherst,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stuart","family":"Russell","sequence":"additional","affiliation":[{"name":"University of California,Berkeley,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shlomo","family":"Zilberstein","sequence":"additional","affiliation":[{"name":"University of Massachusetts,Amherst,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"State abstractions for lifelong reinforcement learning","author":"Abel","year":"2018","journal-title":"ICML"},{"key":"ref2","article-title":"Markovian state and action abstractions for MDPs via hierarchical MCTS","author":"Bai","year":"2016","journal-title":"IJCAI"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3414"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v32i1.19842"},{"key":"ref5","article-title":"CAMPS: Learning context-specific abstractions for efficient planning","author":"Chitnis","year":"2020","journal-title":"arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-036-2.50067-9"},{"key":"ref7","article-title":"Learning task informed abstractions","author":"Fu","year":"2021","journal-title":"38th ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/s0004-3702(00)00068-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11206-0_29"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-203-8.50023-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5483"},{"key":"ref12","article-title":"Abstraction selection in model-based reinforcement learning","author":"Jiang","year":"2015","journal-title":"ICML"},{"issue":"2","key":"ref13","article-title":"Generating abstractions for planning","volume":"68","author":"Knoblock","year":"1994","journal-title":"AIJ"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"key":"ref15","article-title":"Towards a unified theory of state abstraction for MDPs","author":"Li","year":"2006","journal-title":"ISAIM"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MRS.2017.8250943"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561435"},{"key":"ref18","article-title":"Policy invariance under reward transformations","author":"Ng","year":"1999","journal-title":"ICML"},{"key":"ref19","article-title":"Soft labeling in stochastic shortest path problems","author":"Pineda","year":"2019","journal-title":"18th AAMAS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11036"},{"key":"ref21","article-title":"Combining dynamic abstractions in large MDPs","author":"Steinkraus","year":"2004","journal-title":"Technical report, MIT"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196898"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967676"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/208"},{"key":"ref25","article-title":"Dynamic choice of state abstraction in Q-learning","author":"Tamassia","year":"2016","journal-title":"ECAI"},{"key":"ref26","article-title":"Model-invariant state abstractions for model-based RL","author":"Tomar","year":"2021","journal-title":"arXiv"},{"key":"ref27","article-title":"Abstraction in problem solving and learning","author":"Unruh","year":"1989","journal-title":"11th IJCAI"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981612.pdf?arnumber=9981612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:00:12Z","timestamp":1706767212000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/9981612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":27,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/iros47612.2022.9981612","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}