{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T09:25:53Z","timestamp":1751534753760,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"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":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683491","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T15:50:18Z","timestamp":1643730618000},"page":"2270-2275","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning"],"prefix":"10.1109","author":[{"given":"Desmond","family":"Cai","sequence":"first","affiliation":[{"name":"AStar,Singapore"}]},{"given":"Shiau Hong","family":"Lim","sequence":"additional","affiliation":[{"name":"IBM Research,Singapore"}]},{"given":"Laura","family":"Wynter","sequence":"additional","affiliation":[{"name":"IBM Research,Singapore"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Bayesian multi-task reinforcement learning","author":"lazaric","year":"2010","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"article-title":"Sharing knowledge in multi-task deep reinforcement learning","year":"0","author":"d\u2019eramo","key":"ref12"},{"key":"ref13","article-title":"Multi-task deep reinforcement learning with popart","author":"hessel","year":"2018","journal-title":"AAAI"},{"key":"ref14","article-title":"Attentive multitask deep reinforcement learning","author":"bram","year":"2019","journal-title":"ECML\/PKDD"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683491"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273624"},{"key":"ref17","first-page":"3041","article-title":"Finite-sample analysis of least-squares policy iteration","volume":"13","author":"lazaric","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","article-title":"Progressive neural networks","volume":"abs 1606 4671","author":"rusu","year":"2016","journal-title":"ArXiv"},{"key":"ref19","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","volume":"abs 1511 6342","author":"parisotto","year":"2015","journal-title":"CoRR"},{"article-title":"Online batch selection for faster training of neural networks","year":"2015","author":"loshchilov","key":"ref28"},{"key":"ref4","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"NIPS"},{"key":"ref27","article-title":"Not all samples are created equal: Deep learning with importance sampling","author":"katharopoulos","year":"2018","journal-title":"ICML"},{"key":"ref3","article-title":"Solar: Deep structured latent representations for model-based reinforcement learning","volume":"abs 1808 9105","author":"zhang","year":"2018","journal-title":"ArXiv"},{"key":"ref6","article-title":"Improving sample efficiency in model-free reinforcement learning from images","volume":"abs 1910 1741","author":"yarats","year":"2019","journal-title":"ArXiv"},{"article-title":"Variance reduction in sgd by distributed importance sampling","year":"2015","author":"alain","key":"ref29"},{"key":"ref5","article-title":"Modeling the long term future in model-based reinforcement learning","author":"ke","year":"2019","journal-title":"ICLRE"},{"key":"ref8","article-title":"Data-efficient model-based reinforcement learning with deep probabilistic dynamics models","author":"chua","year":"2018","journal-title":"NIPS 2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013870"},{"key":"ref2","article-title":"Model-based reinforcement learning via meta-policy optimization","volume":"abs 1809 5214","author":"clavera","year":"2018","journal-title":"ArXiv"},{"key":"ref9","article-title":"The bottleneck simulator: A model-based deep reinforcement learning approach","volume":"abs 1807 4723","author":"serban","year":"2018","journal-title":"ArXiv"},{"key":"ref1","article-title":"Algorithmic framework for model-based reinforcement learning with theoretical guarantees","volume":"abs 1807 3858","author":"xu","year":"2019","journal-title":"ArXiv"},{"key":"ref20","article-title":"Distral: Robust multitask reinforcement learning","author":"teh","year":"2017","journal-title":"NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/505"},{"key":"ref21","article-title":"Learning values across many orders of magnitude","author":"van hasselt","year":"2016","journal-title":"NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref23","first-page":"590","article-title":"PIC: permutation invariant critic for multi-agent deep reinforcement learning","author":"liu","year":"2019","journal-title":"3rd Annual Conference on Robot Learning CoRL 2019 Osaka Japan October 30 - November 1 2019 Proceedings"},{"article-title":"A deep reinforcement learning framework for the financial portfolio management problem","year":"2017","author":"jiang","key":"ref26"},{"key":"ref25","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2021,12,14]]},"location":"Austin, TX, USA","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683491.pdf?arnumber=9683491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T16:24:23Z","timestamp":1654532663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683491","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}