{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:33:21Z","timestamp":1763202801521},"reference-count":40,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191425","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T13:30:03Z","timestamp":1690983003000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Variational Skill Embeddings for Meta Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jen-Tzung","family":"Chien","sequence":"first","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Weiwei","family":"Lai","sequence":"additional","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Diversity is all you need: learning skills without a reward function","author":"eysenbach","year":"2019","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref35","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref12","article-title":"Variational intrinsic control","author":"gregor","year":"2017","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref34","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"jang","year":"2017","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref15","article-title":"ProMP: Proximal meta-policy search","author":"rothfuss","year":"2019","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3235202"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287440"},{"key":"ref36","first-page":"2028","article-title":"Model-based soft actor-critic","author":"chien","year":"2021","journal-title":"Proc of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference"},{"key":"ref31","article-title":"Deep variational information bottleneck","author":"alemi","year":"2017","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref30","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref11","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"2020","journal-title":"Proc of conference on robot learning"},{"key":"ref33","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094860"},{"key":"ref32","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412170"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-832"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2499302"},{"key":"ref38","first-page":"1611","article-title":"Multiple target prediction for deep reinforcement learning","author":"chien","year":"2020","journal-title":"Proc of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference"},{"key":"ref19","first-page":"424","article-title":"AVAST: Attentive variational state tracker in a reinforced navigator","author":"jang","year":"2022","journal-title":"Proc of International Joint Conference on Natural Language Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687925"},{"key":"ref24","article-title":"Sub-policy adaptation for hierarchical reinforcement learning","author":"li","year":"2020","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref25","article-title":"Hierarchical reinforcement learning by discovering intrinsic options","author":"zhang","year":"2021","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref20","article-title":"Meta-Q-learning","author":"fakoor","year":"2020","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref22","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref21","article-title":"Dynamics-aware unsupervised discovery of skills","author":"sharma","year":"2020","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1383"},{"key":"ref27","article-title":"Meta learning shared hierarchies","author":"frans","year":"2018","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref29","article-title":"Learning an embedding space for transferable robot skills","author":"hausman","year":"2018","journal-title":"Proc of International Conference on Learning Representations"},{"key":"ref8","article-title":"RL2: fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref9","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"2019","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref4","article-title":"Skill-based meta-reinforcement learning","author":"nam","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000037"},{"key":"ref6","first-page":"21050","article-title":"Biased gradient estimate with drastic variance reduction for meta reinforcement learning","author":"tang","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref40","article-title":"Multi-task reinforcement learning with soft modularization","author":"yang","year":"2020","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\/10191425.pdf?arnumber=10191425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T13:43:37Z","timestamp":1692625417000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191425","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}