{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:25:26Z","timestamp":1730204726795,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"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":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992504","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"4884-4891","source":"Crossref","is-referenced-by-count":0,"title":["Polya Decision Processes: A New History-Dependent Framework for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Masahiro","family":"Kohjima","sequence":"first","affiliation":[{"name":"NTT Corporation,NTT Human Informatics Laboratories,Yokosuka,Japan,Kanagawa 239-0847"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Reinforcement learning: An introduction.","year":"2018","author":"Sutton","key":"ref1"},{"journal-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming.","year":"2005","author":"Puterman","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/zamm.19230030407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277770"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357241"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/700"},{"article-title":"Deep recurrent q-learning for partially observable mdps","year":"2015","author":"Hausknecht","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052644"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.008"},{"key":"ref12","first-page":"239","article-title":"A POMDP formulation of preference elicitation problems","volume-title":"AAAI Conf. on Artificial Intelligence","author":"Boutilier"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799381"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50052-9"},{"key":"ref15","first-page":"1088","article-title":"Approximating optimal policies for partially observable stochastic domains","volume-title":"International Joint Conferences on Artificial Intelligence","author":"Parr"},{"key":"ref16","first-page":"1036","article-title":"Reinforcement learning using approximate belief states","author":"Rodriguez","year":"2000","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"1555","article-title":"Predictive representations of state","author":"Littman","year":"2001","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"712","article-title":"Learning predictive state representations","volume-title":"International Conference on Machine Learning","author":"Singh"},{"issue":"1","key":"ref19","first-page":"3395","article-title":"Efficient learning and planning with compressed predictive states","volume":"15","author":"Hamilton","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"volume-title":"Combinatorial stochastic processes: Ecole d\u2019et\u00e9 de probabilit\u00e9s de saint-flour xxxii-2002","year":"2006","author":"Pitman","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380044"},{"volume-title":"The witness algorithm: Solving partially observable markov decision processes","year":"1994","author":"Littman","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.28.1.1"},{"key":"ref24","first-page":"1025","article-title":"Point-based value iteration: An anytime algorithm for pomdps","volume-title":"International Joint Conferences on Artificial Intelligence","author":"Pineau"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","year":"2020","author":"Levine","key":"ref27"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","start":{"date-parts":[[2022,12,6]]},"location":"Cancun, Mexico","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992504.pdf?arnumber=9992504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:28:38Z","timestamp":1709371718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992504","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}