{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:08:31Z","timestamp":1729631311321,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,10]]},"DOI":"10.1109\/icsmc.2008.4811303","type":"proceedings-article","created":{"date-parts":[[2009,4,8]],"date-time":"2009-04-08T09:25:32Z","timestamp":1239182732000},"page":"365-372","source":"Crossref","is-referenced-by-count":0,"title":["Learning task decomposition and exploration shaping for reinforcement learning agents"],"prefix":"10.1109","author":[{"given":"Predrag","family":"Djurdjevic","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manfred","family":"Huber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"0","key":"19"},{"key":"17","article-title":"anticipatory learning for focusing search in learning agents, 2004","author":"hayes","year":"2004","journal-title":"Proc ABiALS"},{"year":"2006","author":"konidaris","article-title":"building portable options: skill transfer in reinforcement learning","key":"18"},{"key":"15","article-title":"accelerating reinforcement learning through the discovery of useful subgoals","author":"mcgovern","year":"2001","journal-title":"Proc 18th"},{"key":"16","article-title":"using relative novelty to identify useful abstractions in reinforcement learning","author":"simsek","year":"2004","journal-title":"Proc 21th"},{"key":"13","doi-asserted-by":"crossref","DOI":"10.1145\/1082473.1082482","article-title":"behaviour transfer of value-function-based reinforcement learning","author":"taylor","year":"2005","journal-title":"Proc of AAMAS'05"},{"key":"14","article-title":"state abstraction discovery from irrelevant variables","author":"jong","year":"2005","journal-title":"Proc IJCAI"},{"year":"0","key":"11"},{"key":"12","article-title":"improving action selection in mdp's via knowledge transfer","author":"shestorov","year":"2005","journal-title":"Proc AAAI"},{"year":"0","key":"21"},{"key":"20","article-title":"estimating future reward in reinforcement learning using associative learning","author":"konidaris","year":"2004","journal-title":"Proc 1st Int Conf on Simulation of Adaptive Behavior"},{"year":"2004","author":"oudeyer","journal-title":"Maximizing learning progress Internal reward system for development","key":"22"},{"year":"1998","author":"drummond","journal-title":"Proc 10th ECML","key":"23"},{"year":"0","key":"24"},{"year":"0","key":"25"},{"key":"26","article-title":"continuous categories for a mobile robot","author":"rosenstein","year":"1999","journal-title":"Proc 10th Nat l Conf AI"},{"key":"27","first-page":"341","article-title":"recent advances in hierarchical reinforcement learning, deds","volume":"4","author":"barto","year":"2003"},{"key":"28","article-title":"finding structure in reinforcement learning","volume":"7","author":"thrun","year":"1995","journal-title":"Advances in neural information processing systems"},{"year":"0","key":"29"},{"key":"3","article-title":"learning skill and representation hierarchies for effective knowledge transfer","author":"asadi","year":"2007","journal-title":"Proceedings of IJCAI-07"},{"year":"0","author":"asadi","article-title":"learning state and action hierarchies for reinforcement learning using autonomous subgoal discovery and action-dependant state space partitioning","key":"2"},{"key":"10","article-title":"defining object types and options using mdp homomorphism","author":"wolfe","year":"2006","journal-title":"Proc ICML-06"},{"year":"2006","author":"papudesi","journal-title":"Learning Behaviorally Grounded State Representations for Reinforcement Learning Agents Epibot","key":"1"},{"key":"7","article-title":"model reduction techniques for computing approximately optimal solutions for markov decision processes","author":"dean","year":"1997","journal-title":"Proc UAI-97"},{"key":"6","article-title":"eligibility traces for off-policy evaluation","author":"precup","year":"2000","journal-title":"Proc 17th"},{"year":"0","author":"shelton","article-title":"policy improvement for pomdps using normalized importance sampling","key":"5"},{"key":"4","article-title":"subgoal discovery for hierarchical reinforcement learning using learned policies","author":"goel","year":"2003","journal-title":"Proc FLAIRS"},{"year":"0","key":"9"},{"key":"8","article-title":"effective online detection of task-independent landmarks","author":"butz","year":"2004","journal-title":"IlliGAL Technical Report"}],"event":{"name":"2008 IEEE International Conference on Systems, Man and Cybernetics (SMC)","start":{"date-parts":[[2008,10,12]]},"location":"Singapore, Singapore","end":{"date-parts":[[2008,10,15]]}},"container-title":["2008 IEEE International Conference on Systems, Man and Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4803719\/4811240\/04811303.pdf?arnumber=4811303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,18]],"date-time":"2017-06-18T14:41:59Z","timestamp":1497796919000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4811303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,10]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icsmc.2008.4811303","relation":{},"ISSN":["1062-922X"],"issn-type":[{"type":"print","value":"1062-922X"}],"subject":[],"published":{"date-parts":[[2008,10]]}}}