{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T09:13:56Z","timestamp":1781255636822,"version":"3.54.1"},"reference-count":70,"publisher":"Elsevier BV","issue":"1-2","license":[{"start":{"date-parts":[[1998,5,1]],"date-time":"1998-05-01T00:00:00Z","timestamp":893980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2013,7,25]],"date-time":"2013-07-25T00:00:00Z","timestamp":1374710400000},"content-version":"vor","delay-in-days":5564,"URL":"https:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artificial Intelligence"],"published-print":{"date-parts":[[1998,5]]},"DOI":"10.1016\/s0004-3702(98)00023-x","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T19:37:38Z","timestamp":1027625858000},"page":"99-134","source":"Crossref","is-referenced-by-count":2389,"title":["Planning and acting in partially observable stochastic domains"],"prefix":"10.1016","volume":"101","author":[{"given":"Leslie Pack","family":"Kaelbling","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael L.","family":"Littman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony R.","family":"Cassandra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/S0004-3702(98)00023-X_bib1","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/0022-247X(65)90154-X","article-title":"Optimal control of Markov decision processes with incomplete state estimation","volume":"10","author":"Astr\u00f6m","year":"1995","journal-title":"J. Math. Anal. Appl."},{"key":"10.1016\/S0004-3702(98)00023-X_bib2","series-title":"Proceedings Thirteenth National Conference on Artificial Intelligence (AAAI-96)","first-page":"1160","article-title":"Rewarding behaviors","author":"Bacchus","year":"1996"},{"key":"10.1016\/S0004-3702(98)00023-X_bib3","volume":"Vols. 1 and 2","author":"Bertsekas","year":"1995"},{"issue":"1\u20132","key":"10.1016\/S0004-3702(98)00023-X_bib4","first-page":"279","article-title":"Fast planning through planning graph analysis","volume":"90","author":"Blum","year":"1997","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0004-3702(98)00023-X_bib5","series-title":"Proceedings Tenth Conference on Uncertainty in Artificial Intelligence (UAI-94)","first-page":"94","article-title":"Planning with external events","author":"Blythe","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib6","series-title":"Proceedings Thirteenth National Conference on Artificial Intelligence (AAAI-96)","first-page":"1168","article-title":"Computing optimal policies for partially observable decision processes using compact representations","author":"Boutilier","year":"1996"},{"key":"10.1016\/S0004-3702(98)00023-X_bib7","series-title":"Proceedings Thirteenth Annual Conference on Uncertainty in Artificial Intelligence (UAI-97)","first-page":"54","article-title":"Incremental Pruning: a simple, fast, exact method for partially observable Markov decision processes","author":"Cassandra","year":"1997"},{"key":"10.1016\/S0004-3702(98)00023-X_bib8","series-title":"Proceedings Twelfth National Conference on Artificial Intelligence (AAAI-94)","first-page":"1023","article-title":"Acting optimally in partially observable stochastic domains","author":"Cassandra","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib9","article-title":"Exact and approximate algorithms for partially observable Markov decision problems","author":"Cassandra","year":"1998"},{"key":"10.1016\/S0004-3702(98)00023-X_bib10","article-title":"Algorithms for partially observable Markov decision processes","author":"Cheng","year":"1988"},{"key":"10.1016\/S0004-3702(98)00023-X_bib11","series-title":"Proceedings Tenth National Conference on Artificial Intelligence (AAAI-92)","first-page":"183","article-title":"Reinforcement learning with perceptual aliasing: The perceptual distinctions approach","author":"Chrisman","year":"1992"},{"issue":"2","key":"10.1016\/S0004-3702(98)00023-X_bib12","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/0890-5401(92)90048-K","article-title":"The complexity of stochastic games","volume":"96","author":"Condon","year":"1992","journal-title":"Inform. and Comput."},{"issue":"1\u20132","key":"10.1016\/S0004-3702(98)00023-X_bib13","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/0004-3702(94)00086-G","article-title":"Planning under time constraints in stochastic domains","volume":"76","author":"Dean","year":"1995","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0004-3702(98)00023-X_bib14","article-title":"Probabilistic planning with information gathering and contingent execution","author":"Draper","year":"1993"},{"key":"10.1016\/S0004-3702(98)00023-X_bib15","series-title":"Proceedings Eighth National Conference on Artificial Intelligence (AAAI-90)","first-page":"138","article-title":"Anytime synthetic projection: maximizing the probability of goal satisfaction","author":"Drummond","year":"1990"},{"issue":"5","key":"10.1016\/S0004-3702(98)00023-X_bib16","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1287\/opre.32.5.1107","article-title":"The optimal search for a moving target when the search path is constrained","volume":"32","author":"Eagle","year":"1984","journal-title":"Oper. Res."},{"key":"10.1016\/S0004-3702(98)00023-X_bib17","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1007\/BF02283610","article-title":"On the average cost optimality equation and the structure of optimal policies for partially observable Markov processes","volume":"29","author":"Fern\u00e1ndez-Gaucherand","year":"1991","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/S0004-3702(98)00023-X_bib18","series-title":"The Second International Conference on Artificial Intelligence Planning Systems","first-page":"80","article-title":"Conditional linear planning","author":"Goldman","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib19","series-title":"Proceedings 10th Conference on Uncertainty in Artificial Intelligence (UAI-94)","first-page":"253","article-title":"Epsilon-safe planning","author":"Goldman","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib20","series-title":"Proceedings 4th International Conference on Principles of Knowledge Representation and Reasoning (KR-94)","first-page":"238","article-title":"Representing uncertainty in simple planners","author":"Goldman","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib21","article-title":"Utility models for goal-directed decision-theoretic planners","author":"Haddawy","year":"1993"},{"key":"10.1016\/S0004-3702(98)00023-X_bib22","series-title":"Proceedings Twelfth National Conference on Artificial Intelligence (AAAI-94)","first-page":"1029","article-title":"Cost-effective sensing during plan execution","author":"Hansen","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib23","article-title":"An improved policy iteration algorithm for partially observable MDPs","volume":"10","author":"Hansen","year":"1998","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/S0004-3702(98)00023-X_bib24","series-title":"Dynamic Programming and Markov Processes","author":"Howard","year":"1960"},{"key":"10.1016\/S0004-3702(98)00023-X_bib25","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/TSSC.1966.300074","article-title":"Information value theory","volume":"1","author":"Howard","year":"1966","journal-title":"IEEE Trans. Systems Science and Cybernetics SSC-2"},{"key":"10.1016\/S0004-3702(98)00023-X_bib26","first-page":"35","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kaiman","year":"1960","journal-title":"Trans, American Society of Mechanical Engineers, Journal of Basic Engineering"},{"key":"10.1016\/S0004-3702(98)00023-X_bib27","article-title":"Optimal probabilistic and decision-theoretic planning using Markovian decision theory","author":"Koenig","year":"1992","journal-title":"Technical Report UCB\/CSD 92\/685"},{"key":"10.1016\/S0004-3702(98)00023-X_bib28","series-title":"Proceedings 4th International Conference on Principles of Knowledge Representation and Reasoning (KR-94)","first-page":"363","article-title":"Risk-sensitive planning with probabilistic decision graphs","author":"Koenig","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib29","series-title":"Genetic Programming: On the Programming of Computers by Means of Natural Selection","author":"Koza","year":"1992"},{"issue":"1\u20132","key":"10.1016\/S0004-3702(98)00023-X_bib30","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/0004-3702(94)00087-H","article-title":"An algorithm for probabilistic planning","volume":"76","author":"Kushmerick","year":"1995","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0004-3702(98)00023-X_bib31","series-title":"Proceedings Third European Workshop on Planning","first-page":"205","article-title":"Generating optimal policies for high-level plans with conditional branches and loops","author":"Lin","year":"1995"},{"key":"10.1016\/S0004-3702(98)00023-X_bib32","series-title":"From Animals to Animals 3: Proceedings Third International Conference on Simulation of Adaptive Behavior","article-title":"Memoryless policies: theoretical limitations and practical results","author":"Littman","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib33","series-title":"Proceedings Twelfth International Conference on Machine Learning","first-page":"362","article-title":"Learning policies for partially observable environments: scaling up","author":"Littman","year":"1995"},{"key":"10.1016\/S0004-3702(98)00023-X_bib34","article-title":"Efficient dynamic-programming updates in partially observable Markov decision processes","author":"Littman","year":"1996"},{"key":"10.1016\/S0004-3702(98)00023-X_bib35_1","article-title":"Algorithms for sequential decision making","author":"Littman","year":"1996"},{"key":"10.1016\/S0004-3702(98)00023-X_bib35_2","unstructured":"also Technical Report CS-96-09"},{"issue":"1","key":"10.1016\/S0004-3702(98)00023-X_bib36","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/BF02055574","article-title":"A survey of algorithmic methods for partially observable Markov decision processes","volume":"28","author":"Lovejoy","year":"1991","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/S0004-3702(98)00023-X_bib37","article-title":"MAXPLAN: a new approach to probabilistic planning","author":"Majercik","year":"1998"},{"key":"10.1016\/S0004-3702(98)00023-X_bib38","series-title":"Proceedings 9th Conference on Uncertainty in Artificial Intelligence (UAI-93)","first-page":"350","article-title":"A method for planning given uncertain and incomplete information","author":"Mansell","year":"1993"},{"key":"10.1016\/S0004-3702(98)00023-X_bib39","series-title":"Proceedings 9th National Conference on Artificial Intelligence (AAAI-91)","first-page":"634","article-title":"Systematic nonlinear planning","author":"McAllester","year":"1991"},{"key":"10.1016\/S0004-3702(98)00023-X_bib40","series-title":"Proceedings Tenth International Conference on Machine Learning","first-page":"190","article-title":"Overcoming incomplete perception with utile distinction memory","author":"McCallum","year":"1993"},{"key":"10.1016\/S0004-3702(98)00023-X_bib41","series-title":"Proceedings Twelfth International Conference on Machine Learning","first-page":"387","article-title":"Instance-based utile distinctions for reinforcement learning with hidden state","author":"McCallum","year":"1995"},{"issue":"1","key":"10.1016\/S0004-3702(98)00023-X_bib42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1287\/mnsc.28.1.1","article-title":"A survey of partially observable Markov decision processes: theory, models, and algorithms","volume":"28","author":"Monahan","year":"1982","journal-title":"Management Science"},{"key":"10.1016\/S0004-3702(98)00023-X_bib43","series-title":"Formal Theories of the Commonsense World","first-page":"319","article-title":"A formal theory of knowledge and action","author":"Moore","year":"1985"},{"key":"10.1016\/S0004-3702(98)00023-X_bib44","series-title":"Proceedings 10th International Joint Conference on Artificial Intelligence (IJCAI-87)","first-page":"867","article-title":"Knowledge preconditions for actions and plans","author":"Morgenstern","year":"1987"},{"key":"10.1016\/S0004-3702(98)00023-X_bib45","series-title":"Proceedings Third International Conference on Principles of Knowledge Representation and Reasoning (KR-92)","first-page":"103","article-title":"UCPOP: a sound, complete, partial order planner for ADL","author":"Penberthy","year":"1992"},{"key":"10.1016\/S0004-3702(98)00023-X_bib46","series-title":"Proceedings First International Conference on Artificial Intelligence Planning Systems","first-page":"189","article-title":"Conditional nonlinear planning","author":"Peot","year":"1992"},{"key":"10.1016\/S0004-3702(98)00023-X_bib47","article-title":"A feasible computational approach to infinite-horizon partially-observed Markov decision problems","author":"Platzman","year":"1981"},{"key":"10.1016\/S0004-3702(98)00023-X_bib48","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1613\/jair.277","article-title":"Planning for contingencies: a decision-based approach","volume":"4","author":"Pryor","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/S0004-3702(98)00023-X_bib49","series-title":"Markov Decision Processes\u2014Discrete Stochastic Dynamic Programming","author":"Puterman","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib50","first-page":"257","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"1989"},{"issue":"1","key":"10.1016\/S0004-3702(98)00023-X_bib51","first-page":"1","article-title":"Optimal control for partially observable Markov decision processes over an infinite horizon","volume":"21","author":"Sawaki","year":"1978","journal-title":"J. Oper. Res. Soc. Japan"},{"key":"10.1016\/S0004-3702(98)00023-X_bib52","series-title":"Proceedings 11th National Conference on Artificial Intelligence (AAAI-93)","first-page":"689","article-title":"The frame problem and knowledge-producing actions","author":"Schert","year":"1993"},{"key":"10.1016\/S0004-3702(98)00023-X_bib53","series-title":"Proceedings Tenth International Joint Conference on Artificial Intelligence (IJCAI-87)","first-page":"1039","article-title":"Universal plans for reactive robots in unpredictable environments","author":"Schoppers","year":"1987"},{"key":"10.1016\/S0004-3702(98)00023-X_bib54","series-title":"Theory of Linear and Integer Programming","author":"Schrijver","year":"1986"},{"key":"10.1016\/S0004-3702(98)00023-X_bib55","series-title":"Proceedings Eleventh International Conference on Machine Learning","first-page":"284","article-title":"Model-free reinforcement learning for non-Markovian decision problems","author":"Singh","year":"1994"},{"key":"10.1016\/S0004-3702(98)00023-X_bib56","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1287\/opre.21.5.1071","article-title":"The optimal control of partially observable Markov processes over a finite horizon","volume":"21","author":"Smallwood","year":"1973","journal-title":"Oper. Res."},{"key":"10.1016\/S0004-3702(98)00023-X_bib57","series-title":"Working Notes for the 1995 Stanford Spring Symposium on Extended Theories of Action","article-title":"Representation and evaluation of plans with loops","author":"Smith","year":"1995"},{"key":"10.1016\/S0004-3702(98)00023-X_bib58","article-title":"The optimal control of partially observable Markov processes","author":"Sondik","year":"1971"},{"issue":"2","key":"10.1016\/S0004-3702(98)00023-X_bib59","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1287\/opre.26.2.282","article-title":"The optimal control of partially observable Markov processes over the infinite horizon: discounted costs","volume":"26","author":"Sondik","year":"1978","journal-title":"Oper. Res."},{"key":"10.1016\/S0004-3702(98)00023-X_bib60","first-page":"11","article-title":"Hidden Markov model induction by Bayesian model merging","volume":"5","author":"Stolcke","year":"1993"},{"key":"10.1016\/S0004-3702(98)00023-X_bib61","series-title":"Proceedings 12th National Conference on Artificial Intelligence (AAAI-94)","first-page":"1079","article-title":"Control strategies for a stochastic planner","author":"Tash","year":"1994"},{"issue":"5","key":"10.1016\/S0004-3702(98)00023-X_bib62","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/0167-6377(90)90022-W","article-title":"Solving H-horizon, stationary Markov decision problems in time proportional to log(H)","volume":"9","author":"Tseng","year":"1990","journal-title":"Oper. Res. Lett."},{"issue":"1","key":"10.1016\/S0004-3702(98)00023-X_bib63","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/BF00934845","article-title":"Application of Jensen's inequality for adaptive suboptimal design","volume":"32","author":"White","year":"1980","journal-title":"J. Optim. Theory Appl."},{"key":"10.1016\/S0004-3702(98)00023-X_bib64","doi-asserted-by":"crossref","DOI":"10.1007\/BF02204836","article-title":"Partially observed Markov decision processes: a survey","volume":"32","author":"White","year":"1991","journal-title":"Ann. Oper. Res."},{"issue":"5","key":"10.1016\/S0004-3702(98)00023-X_bib65","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1287\/opre.37.5.791","article-title":"Solution procedures for partially observed Markov decision processes","volume":"37","author":"White","year":"1989","journal-title":"Oper. Res."},{"key":"10.1016\/S0004-3702(98)00023-X_bib66","article-title":"Tight performance bounds on greedy policies based on imperfect value functions","author":"Williams","year":"1993"},{"key":"10.1016\/S0004-3702(98)00023-X_bib67","article-title":"Planning in stochastic domains: problem characteristics and approximation","author":"Zhang","year":"1996"},{"key":"10.1016\/S0004-3702(98)00023-X_bib68","series-title":"From Animals to Animals: Proceedings Fourth International Conference on Simulation of Adaptive Behavior","first-page":"516","article-title":"Incremental self-improvement for life-time multi-agent reinforcement learning","author":"Zhao","year":"1996"},{"issue":"1\u20132","key":"10.1016\/S0004-3702(98)00023-X_bib69","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/0304-3975(95)00188-3","article-title":"The complexity of mean payoff games on graphs","volume":"158","author":"Zwick","year":"1996","journal-title":"Theoret. Comput. Sci."}],"container-title":["Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S000437029800023X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S000437029800023X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,1,29]],"date-time":"2020-01-29T07:00:14Z","timestamp":1580281214000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S000437029800023X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,5]]},"references-count":70,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[1998,5]]}},"alternative-id":["S000437029800023X"],"URL":"https:\/\/doi.org\/10.1016\/s0004-3702(98)00023-x","relation":{},"ISSN":["0004-3702"],"issn-type":[{"value":"0004-3702","type":"print"}],"subject":[],"published":{"date-parts":[[1998,5]]}}}