{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:25:14Z","timestamp":1740101114393,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T00:00:00Z","timestamp":1666137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T00:00:00Z","timestamp":1666137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,19]]},"DOI":"10.1109\/kse56063.2022.9953750","type":"proceedings-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T21:25:53Z","timestamp":1669065953000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization"],"prefix":"10.1109","author":[{"given":"Bang Giang","family":"Le","sequence":"first","affiliation":[{"name":"VNU University of Engineering and Technology,HMI Lab,Hanoi,Vietnam"}]},{"given":"Viet Cuong","family":"Ta","sequence":"additional","affiliation":[{"name":"VNU University of Engineering and Technology,HMI Lab,Hanoi,Vietnam"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Information asymmetry in kl-regularized rl","author":"galashov","year":"2019","journal-title":"arXiv preprint arXiv 1905 09010"},{"key":"ref32","article-title":"Double q-learning","volume":"23","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref31","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref10","first-page":"11 501","article-title":"Conservative data sharing for multi-task offline reinforcement learning","volume":"34","author":"yu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Cog: Connecting new skills to past experience with offline reinforcement learning","author":"singh","year":"2020","journal-title":"arXiv preprint arXiv 2010 14318"},{"key":"ref12","article-title":"Learning robust state abstractions for hidden-parameter block mdps","author":"zhang","year":"2020","journal-title":"arXiv preprint arXiv 2007 02214"},{"key":"ref13","article-title":"Hierarchical and interpretable skill acquisition in multi-task reinforcement learning","author":"shu","year":"2017","journal-title":"arXiv preprint arXiv 1712 07294"},{"key":"ref14","article-title":"Behavior regularized offline reinforcement learning","author":"wu","year":"2019","journal-title":"arXiv preprint arXiv 1911 12945"},{"key":"ref15","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume":"26","author":"cuturi","year":"2013","journal-title":"Advances in neural information processing systems"},{"article-title":"Wasserstein gan","year":"2017","author":"arjovsky","key":"ref16"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref17"},{"key":"ref18","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref28","article-title":"Primal wasserstein imitation learning","author":"dadashi","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref4","article-title":"Distral: Robust multitask reinforcement learning","volume":"30","author":"teh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20645"},{"key":"ref3","first-page":"1","article-title":"Sharing knowledge in multi-task deep reinforcement learning","author":"d\u2019eramo","year":"2020","journal-title":"in International Conference on Learning Representations OpenReview net"},{"key":"ref6","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"yu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Imitation learning with sinkhorn distances","author":"papagiannis","year":"2020","journal-title":"arXiv preprint arXiv 2008 09234"},{"key":"ref5","article-title":"Policy distillation","author":"rusu","year":"2015","journal-title":"arXiv preprint arXiv 1511 06295"},{"key":"ref8","article-title":"Hindsight experience replay","volume":"30","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"In defense of the unitary scalarization for deep multi-task learning","author":"kurin","year":"2022","journal-title":"arXiv preprint arXiv 2201 04122"},{"key":"ref2","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref9","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","author":"sodhani","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref1","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"},{"key":"ref20","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":"International Conference on Machine Learning"},{"key":"ref22","article-title":"Safe and efficient off-policy reinforcement learning","volume":"29","author":"munos","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Q(?) with off-policy corrections","volume":"abs 1602 4951","author":"harutyunyan","year":"2016","journal-title":"CoRR"},{"key":"ref24","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/505"},{"key":"ref26","article-title":"Taming the noise in reinforcement learning via soft updates","author":"fox","year":"2015","journal-title":"arXiv preprint arXiv 1512 08571"},{"key":"ref25","first-page":"4936","article-title":"Importance weighted transfer of samples in reinforcement learning","author":"tirinzoni","year":"2018","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","start":{"date-parts":[[2022,10,19]]},"location":"Nha Trang, Vietnam","end":{"date-parts":[[2022,10,21]]}},"container-title":["2022 14th International Conference on Knowledge and Systems Engineering (KSE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9953734\/9953612\/09953750.pdf?arnumber=9953750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:52:56Z","timestamp":1670874776000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9953750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/kse56063.2022.9953750","relation":{},"subject":[],"published":{"date-parts":[[2022,10,19]]}}}