{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:57:04Z","timestamp":1773154624602,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"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":[[2023,11,9]]},"DOI":"10.1109\/icdl55364.2023.10364342","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:40:19Z","timestamp":1703533219000},"page":"28-36","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Empowerment to Model Tool Use in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Faizan","family":"Rasheed","sequence":"first","affiliation":[{"name":"School of Physics, Engineering, and Computer Science, University of Hertfordshire,Adaptive Systems Research Group,Hatfield,UK,AL10 9AB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Polani","sequence":"additional","affiliation":[{"name":"School of Physics, Engineering, and Computer Science, University of Hertfordshire,Adaptive Systems Research Group,Hatfield,UK,AL10 9AB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicola Catenacci","family":"Volpi","sequence":"additional","affiliation":[{"name":"School of Physics, Engineering, and Computer Science, University of Hertfordshire,Adaptive Systems Research Group,Hatfield,UK,AL10 9AB"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.1322"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.50.1.21"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2005.1554676"},{"key":"ref4","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","author":"Riedmiller","journal-title":"2018 Int. Con. on Machine Learning (ICML)"},{"key":"ref5","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","author":"Mohamed","journal-title":"2015 Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2007.4354064"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2011.6147553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2014.6983027"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329804"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2986411"},{"issue":"1","key":"ref11","first-page":"6818","article-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","volume":"23","author":"Forestier","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-53734-9_4"},{"key":"ref13","article-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2018","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Mutual information state intrinsic control","author":"Zhao","journal-title":"2021 9th Int. Conf. on Learning Representations (ICLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10087-8"},{"key":"ref16","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2011.6037367"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00985"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/e25020327"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref21","volume-title":"Foundations of deep reinforcement learning","author":"Graesser","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3042938"}],"event":{"name":"2023 IEEE International Conference on Development and Learning (ICDL)","location":"Macau, China","start":{"date-parts":[[2023,11,9]]},"end":{"date-parts":[[2023,11,11]]}},"container-title":["2023 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10364334\/10364349\/10364342.pdf?arnumber=10364342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T22:48:15Z","timestamp":1705099695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10364342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icdl55364.2023.10364342","relation":{},"subject":[],"published":{"date-parts":[[2023,11,9]]}}}