{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:20:15Z","timestamp":1766132415632,"version":"3.48.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246876","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"9768-9775","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Gawon","family":"Lee","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Aerospace Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daesol","family":"Cho","sequence":"additional","affiliation":[{"name":"Seoul National University,Artificial Intelligence Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H. Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Aerospace Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"The fractal geometry of nature\/revised and enlarged edition","year":"1983","author":"Mandelbrot","key":"ref1"},{"key":"ref2","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018","journal-title":"A Bradford Book"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref4"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"Lillicrap","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091363"},{"key":"ref7","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on robot learning","author":"Yu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3520894"},{"article-title":"Multi-task reinforcement learning with mixture of orthogonal experts","year":"2023","author":"Hendawy","key":"ref9"},{"key":"ref10","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"International Conference on Machine Learning","author":"Sodhani"},{"key":"ref11","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"},{"article-title":"QMP: Q-switch mixture of policies for multi-task behavior sharing","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang","key":"ref12"},{"article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","year":"2021","author":"Kalashnikov","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref15"},{"key":"ref16","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"},{"article-title":"Temporally-extended {\\epsilon}-greedy exploration","year":"2020","author":"Dabney","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3747"},{"article-title":"Sample efficient myopic exploration through multitask reinforcement learning with diverse tasks","year":"2024","author":"Xu","key":"ref19"},{"article-title":"When should agents explore?","year":"2021","author":"Pislar","key":"ref20"},{"key":"ref21","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"International conference on machine learning","author":"Espeholt"},{"key":"ref22","first-page":"11501","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":"ref23","first-page":"21495","article-title":"Paco: Parametercompositional multi-task reinforcement learning","volume":"35","author":"Sun","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29129"},{"key":"ref25","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Multi-task learning as a bargaining game","year":"2022","author":"Navon","key":"ref26"},{"article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","year":"2015","author":"Parisotto","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.64434\/tml.20251027"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","year":"2017","author":"Achiam","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s12064-011-0142-z"},{"article-title":"Maxinforl: Boosting exploration in reinforcement learning through information gain maximization","year":"2024","author":"Sukhija","key":"ref32"},{"volume-title":"Markov decision processes: discrete stochastic dynamic programming","year":"2014","author":"Puterman","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/381413a0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1318616111"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1186\/s40462-019-0153-9"},{"key":"ref37","first-page":"1179","article-title":"Conservative qlearning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Haarnoja","key":"ref38"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref39"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246876.pdf?arnumber=11246876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:17:17Z","timestamp":1766132237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246876\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246876","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}