{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:21:14Z","timestamp":1771064474900,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10649914","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["TaCoD: Tasks-Commonality-Aware World in Meta Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xuantang","family":"Xiong","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence University of Chinese Academy of Sciences,Beijing,China"}]},{"given":"Shuang","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences,Beijing,China"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation Chinese Academy of Sciences,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref2","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref3","article-title":"Solving rubik\u2019s cube with a robot hand","author":"Akkaya","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447360"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31635-3_22"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3233\/faia230588"},{"key":"ref9","article-title":"A unified view on solving objective mismatch in model-based reinforcement learning","author":"Wei","year":"2023"},{"key":"ref10","article-title":"Objective mismatch in model-based reinforcement learning","author":"Lambert","year":"2020"},{"key":"ref11","first-page":"36470","article-title":"Live in the moment: Learning dynamics model adapted to evolving policy","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref12","article-title":"Deepmind control suite","author":"Tassa","year":"2018"},{"key":"ref13","first-page":"23230","article-title":"Mismatched no more: Joint model-policy optimization for model-based rl","volume":"35","author":"Eysenbach","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","volume-title":"Policy-aware model learning for policy gradient methods","author":"Abachi","year":"2020"},{"key":"ref15","first-page":"259","article-title":"Learning policy-aware models for model-based reinforcement learning via transition occupancy matching","volume-title":"Learning for Dynamics and Control Conference","author":"Ma"},{"key":"ref16","first-page":"1486","article-title":"Value-aware loss function for model-based reinforcement learning","volume-title":"Artificial Intelligence and Statistics.","author":"Farahmand","year":"2017"},{"key":"ref17","article-title":"Value gradient weighted model-based reinforcement learning","author":"Voelcker","year":"2022"},{"key":"ref18","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref19","article-title":"Iterative value-aware model learning","volume":"31","author":"Farahmand","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Lee"},{"key":"ref21","article-title":"Meta-learning surrogate models for sequential decision making","author":"Galashov","year":"2019"},{"key":"ref22","first-page":"23055","article-title":"Model-based meta reinforcement learning using graph structured surrogate models and amortized policy search","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref23","first-page":"1612","article-title":"Minimax model learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Voloshin"},{"key":"ref24","first-page":"5541","article-title":"The value equivalence principle for model-based reinforcement learning","volume":"33","author":"Grimm","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"7773","article-title":"Proper value equivalence","volume":"34","author":"Grimm","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"Promp: Proximal meta-policy search","author":"Rothfuss","year":"2018"},{"key":"ref27","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref28","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"International conference on machine learning","author":"Rakelly"},{"key":"ref29","article-title":"Meta reinforcement learning as task inference","author":"Humplik","year":"2019"},{"key":"ref30","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"Nagabandi","year":"2018"},{"key":"ref31","article-title":"Meta reinforcement learning with latent variable gaussian processes","author":"S\u00e6mundsson","year":"2018"},{"key":"ref32","first-page":"10161","article-title":"Model-based adversarial meta-reinforcement learning","volume":"33","author":"Lin","year":"2020","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10649914.pdf?arnumber=10649914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:50:37Z","timestamp":1725943837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10649914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10649914","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}