{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:41:29Z","timestamp":1760420489750,"version":"build-2065373602"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"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":[[2025,5,23]]},"DOI":"10.1109\/icmlt65785.2025.11193252","type":"proceedings-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:39:05Z","timestamp":1760377145000},"page":"141-149","source":"Crossref","is-referenced-by-count":0,"title":["Contextual Deep Reinforcement Learning with Adaptive Value-based Clustering"],"prefix":"10.1109","author":[{"given":"Yuhe","family":"Gao","sequence":"first","affiliation":[{"name":"Amazon,Seattle,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runzhe","family":"Wan","sequence":"additional","affiliation":[{"name":"Amazon,Jersey City,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Giannakakis","sequence":"additional","affiliation":[{"name":"Amazon,Seattle,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinxiang","family":"Gu","sequence":"additional","affiliation":[{"name":"Amazon,Seattle,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Song","sequence":"additional","affiliation":[{"name":"Amazon,Seattle,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_5781"},{"key":"ref2","first-page":"9216","article-title":"Self-paced deep reinforcement learning","volume":"33","author":"Klink","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","first-page":"2948","article-title":"Self-paced context evaluation for contextual reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Eimer"},{"key":"ref4","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"International Conference on Machine Learning","author":"Sodhani"},{"article-title":"Contextual markov decision processes using generalized linear models","year":"2019","author":"Modi","key":"ref5"},{"key":"ref6","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume":"96","author":"Ester","year":"1996","journal-title":"kdd"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-28349-8_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISPACS.2005.1595432"},{"article-title":"Divide-and-conquer reinforcement learning","year":"2017","author":"Ghosh","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-33-4084-8_12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3100291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330968"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"article-title":"Reinforcement learning with heterogeneous data: estimation and inference","year":"2022","author":"Chen","key":"ref18"},{"key":"ref19","first-page":"1312","article-title":"Universal value function approximators","volume-title":"International conference on machine learning","author":"Schaul"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345339"},{"issue":"946-948","key":"ref21","first-page":"116","article-title":"Sur les transformations isom\u00e9triques d\u2019espaces vectoriels norm\u00e9s","volume":"194","author":"Mazur","year":"1932","journal-title":"CR Acad. Sci. Paris"},{"key":"ref22","first-page":"486","article-title":"A theoretical analysis of deep q-learning","volume-title":"Learning for dynamics and control","author":"Fan","year":"2020"},{"article-title":"Carl: A benchmark for contextual and adaptive reinforcement learning","year":"2021","author":"Benjamins","key":"ref23"},{"article-title":"Or-gym: A reinforcement learning library for operations research problems","year":"2020","author":"Hubbs","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-112723-034423"}],"event":{"name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","start":{"date-parts":[[2025,5,23]]},"location":"Helsinki, Finland","end":{"date-parts":[[2025,5,25]]}},"container-title":["2025 10th International Conference on Machine Learning Technologies (ICMLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11192828\/11192850\/11193252.pdf?arnumber=11193252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:10:10Z","timestamp":1760418610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11193252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icmlt65785.2025.11193252","relation":{},"subject":[],"published":{"date-parts":[[2025,5,23]]}}}