{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T06:59:40Z","timestamp":1742799580716,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1109\/icsmc.2007.4413971","type":"proceedings-article","created":{"date-parts":[[2008,7,18]],"date-time":"2008-07-18T13:19:35Z","timestamp":1216387175000},"page":"1624-1629","source":"Crossref","is-referenced-by-count":1,"title":["States evolution in Θ(λ)-learning based on logical MDPs with negation"],"prefix":"10.1109","author":[{"family":"Song Zhiwei","sequence":"first","affiliation":[]},{"family":"Chen Xiaoping","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","first-page":"293","article-title":"Negation as failure","author":"clark","year":"1977","journal-title":"Logic and Data Bases"},{"key":"17","article-title":"Generalizing plans to new environments in relational MDPs","author":"guestrin","year":"2003","journal-title":"IJCAV03"},{"journal-title":"Foundations of Inductive Logic Programing vol 1228 of Lecture Notes in Artifical Intelligence","year":"1997","author":"neinhuys-cheng","key":"18"},{"key":"15","article-title":"Reinforcement learning for relational MDPs","author":"van otterlo","year":"2004","journal-title":"Machine Learning Conference of Belgium and The Netherlands"},{"key":"16","article-title":"Scaling up reinforcement learning with a relational representation","author":"morales","year":"2003","journal-title":"Proceedings of the Workshop on Adaptability in Multi-agent Systems at AORC'03"},{"key":"13","first-page":"690","article-title":"Symbolic dynamic programming for first-order MDPs","author":"boutilier","year":"2001","journal-title":"Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-01)"},{"key":"14","article-title":"Logical markov decision programs","author":"kersting","year":"2003","journal-title":"IJCAI'03 Workshop on Learning Statistical Models of Relational Data"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102376"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143851"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30109-7_16"},{"key":"20","article-title":"Challenges for relational reinforcement learning","author":"van otterlo","year":"2004","journal-title":"Proceedings of the ICML'04 workshop on Relational Reinfocement Learning"},{"key":"22","first-page":"726","article-title":"Input generalization in delayed reinforcement learning: An algorithm and performance comparisions","author":"chapman","year":"1991","journal-title":"Proceedings of the 12th International Joint Conference on Artificial Intelligence"},{"journal-title":"Reinforcement Learning with Selective Perception and Hidden State","year":"1995","author":"mccallum","key":"23"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993591"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00034-4"},{"key":"26","article-title":"Speeding up relational reinforcement learning through the use of an incremental first order decision tree learner","volume":"2167","author":"driessens","year":"2001","journal-title":"Lecture Notes in Computer Science"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"3"},{"key":"2","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10","article-title":"Approximate policy iteration with a policy language bias","author":"fern","year":"2003","journal-title":"NIPS'03"},{"key":"1","article-title":"Unique state and automatical action abstracting based on logical MDPs with negation","author":"song","year":"2006","journal-title":"Proc 1st Int Conf Natural Comput"},{"key":"7","article-title":"Graph kernels and gaussian processes for relational reinforcement learning","author":"gartner","year":"2003","journal-title":"ILP'03"},{"key":"6","article-title":"Relational instrance based regression for relational reinforcement learning","author":"driessens","year":"2003","journal-title":"ICML 2003"},{"key":"5","article-title":"A survey of reinforcement learning in relational domains","author":"van otterlo","year":"0","journal-title":"CTIT Technical report series"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007694015589"},{"key":"9","volume":"uav02","author":"yoon","year":"2002","journal-title":"Inductive policy selection for firstorder MDPs"},{"key":"8","article-title":"Symbolic learning for adaptive agents","author":"cole","year":"2003","journal-title":"The Annual Partner Conference Smart Internet Technology Cooperative Research Centre"}],"event":{"name":"2007 IEEE International Conference on Systems, Man and Cybernetics","start":{"date-parts":[[2007,10,7]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2007,10,10]]}},"container-title":["2007 IEEE International Conference on Systems, Man and Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4413560\/4413561\/04413971.pdf?arnumber=4413971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,12]],"date-time":"2019-05-12T15:37:33Z","timestamp":1557675453000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4413971\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icsmc.2007.4413971","relation":{},"subject":[],"published":{"date-parts":[[2007]]}}}