{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T07:04:34Z","timestamp":1729667074450,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8594242","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"2997-3003","source":"Crossref","is-referenced-by-count":3,"title":["Accelerating Learning in Constructive Predictive Frameworks with the Successor Representation"],"prefix":"10.1109","author":[{"given":"Craig","family":"Sherstan","sequence":"first","affiliation":[]},{"given":"Marlos C.","family":"Machado","sequence":"additional","affiliation":[]},{"given":"Patrick M.","family":"Pilarski","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","first-page":"1312","article-title":"Universal Value Function Approximators","author":"schaul","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref10","first-page":"510","article-title":"Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement","author":"barreto","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref11","volume":"1212","author":"zeiler","year":"2012","journal-title":"ADADELTA An Adaptive Learning Rate Method"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/1059712313511648"},{"key":"ref13","volume":"1606","author":"kulkarni","year":"2016","journal-title":"Deep successor reinforcement learning"},{"key":"ref14","volume":"1708","author":"lehnert","year":"2017","journal-title":"Advantages and Limitations of Using Successor Features for Transfer in Reinforcement Learning"},{"key":"ref15","first-page":"990","article-title":"Universal Option Models","author":"yao","year":"2014","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.60"},{"key":"ref18","volume":"1804","author":"ma","year":"2018","journal-title":"Universal Successor Representations for Transfer Reinforcement Learning"},{"key":"ref19","article-title":"Eigenoption Discovery through the Deep Successor Representation","author":"machado","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref28","article-title":"Approximate Linear Successor Representation","author":"gehring","year":"2015","journal-title":"Reinforcement Learning Decision Making (RLDM)"},{"key":"ref4","first-page":"761","article-title":"Horde: a Scalable Real-time Architecture for Learning Knowledge from Unsupervised Sensorimotor Interaction","author":"sutton","year":"2011","journal-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref27","first-page":"875","article-title":"Online Discovery and Learning of Predictive State Representations","author":"mccracken","year":"2006","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11813","article-title":"Source Traces for Temporal Difference Learning","author":"pitis","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the Game of Go Without Human Knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level Control through Deep Reinforcement Learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"journal-title":"Continual Learning in Reinforcement Environments","year":"1994","author":"ring","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4378.001.0001","author":"drescher","year":"1991","journal-title":"Made-up Minds A Constructivist Approach to Artificial Intelligence"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2015.7281168"},{"key":"ref22","article-title":"Directly Estimating the Variance of the $A$ -Return Using Temporal-Difference Methods","author":"sherstan","year":"2018","journal-title":"Conference on Uncertainty in Artificial Intelligence (UAI)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2013.6650435"},{"key":"ref24","article-title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","author":"jaderberg","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1007\/978-3-319-41649-6_26","article-title":"Intro-spective Agents: Confidence Measures for General Value Functions","author":"sherstan","year":"2016","journal-title":"International Conference on Artificial General Intelligence (AGI)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390236"},{"key":"ref25","volume":"1807","author":"schlegel","year":"2018","journal-title":"General Value Function Networks"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2018,10,1]]},"location":"Madrid","end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08594242.pdf?arnumber=8594242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T08:33:23Z","timestamp":1720946003000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8594242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8594242","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}