{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:41:11Z","timestamp":1740102071727,"version":"3.37.3"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DE200100245"],"award-info":[{"award-number":["DE200100245"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191360","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework"],"prefix":"10.1109","author":[{"given":"JaeYoon","family":"Kim","sequence":"first","affiliation":[{"name":"Australian Artificial Intelligence Institute (AAII), University of Technology Sydney,Australia"}]},{"given":"Junyu","family":"Xuan","sequence":"additional","affiliation":[{"name":"Australian Artificial Intelligence Institute (AAII), University of Technology Sydney,Australia"}]},{"given":"Christy","family":"Liang","sequence":"additional","affiliation":[{"name":"Visualisation Institute, University of Technology Sydney,Australia"}]},{"given":"Farookh","family":"Hussain","sequence":"additional","affiliation":[{"name":"Australian Artificial Intelligence Institute (AAII), University of Technology Sydney,Australia"}]}],"member":"263","reference":[{"key":"ref13","article-title":"When should agents explore?","author":"pislar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Deep exploration via bootstrapped dqn","volume":"29","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920231"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref11","first-page":"4333","article-title":"Memory based trajectory-conditioned policies for learning from sparse rewards","volume":"33","author":"guo","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Go-explore: a new approach for hard-exploration problems","author":"ecoffet","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Exploration by random network distillation","author":"burda","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Ex2: Exploration with exemplar models for deep reinforcement learning","volume":"30","author":"fu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Temporal difference uncertainties as a signal for exploration","author":"flennerhag","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume":"31","author":"buckman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"648","article-title":"A bayesian approach to robust reinforcement learning","author":"derman","year":"2020","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/09540090802091917"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01849-3"},{"key":"ref23","first-page":"3130","article-title":"Discovering options for exploration by minimizing cover time","author":"jinnai","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref26","first-page":"1851","article-title":"Latent space policies for hierarchical reinforcement learning","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref20","first-page":"12849","article-title":"Tactical optimism and pessimism for deep reinforcement learning","volume":"34","author":"moskovitz","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Adaptive skills adaptive partitions (asap)","volume":"29","author":"mankowitz","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref8","article-title":"Never give up: Learning directed exploration strategies","author":"badia","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Variational option discovery algorithms","author":"achiam","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Episodic curiosity through reachability","author":"savinov","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Large-scale study of curiosity-driven learning","author":"burda","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume":"30","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Variational intrinsic control","author":"gregor","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"2018","journal-title":"ArXiv Preprint"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191360.pdf?arnumber=10191360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:41:38Z","timestamp":1692639698000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191360","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}