{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:42:03Z","timestamp":1730266923804,"version":"3.28.0"},"reference-count":28,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010450","name":"Nova","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010450","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","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\/ijcnn60899.2024.10651458","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":0,"title":["Extraction and Transfer of General Deep Feature in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Min","family":"Chen","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}]},{"given":"Yi","family":"Pan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}]},{"given":"Zhiqiang","family":"Pu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}]},{"given":"Jianqiang","family":"Yi","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}]},{"given":"Shijie","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}]},{"given":"Boyin","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}]}],"member":"263","reference":[{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"article-title":"Situated mapping for transfer learning","volume-title":"Fourth annual conference on advances in cognitive systems","author":"Fitzgerald","key":"ref4"},{"key":"ref5","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"International conference on machine learning","author":"MacGlashan"},{"article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","year":"2022","author":"Bai","key":"ref6"},{"issue":"1","key":"ref7","first-page":"7382","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref8","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"International Conference on Machine Learning","author":"Yarats"},{"key":"ref9","first-page":"25502","article-title":"Why generalization in rl is difficult: Epistemic pomdps and implicit partial observability","volume":"34","author":"Ghosh","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"On catastrophic interference in atari 2600 games","year":"2020","author":"Fedus","key":"ref10"},{"key":"ref11","first-page":"2063","article-title":"Transfer learning for related reinforcement learning tasks via image-to-image translation","volume-title":"International conference on machine learning","author":"Gamrian"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160557"},{"key":"ref13","first-page":"2299","article-title":"Cross-domain adaptive transfer reinforcement learning based on state-action correspondence","volume-title":"Uncertainty in Artificial Intelligence","author":"You","year":"2022"},{"article-title":"Mutual information based knowledge transfer under state-action dimension mismatch","year":"2020","author":"Wan","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref17","first-page":"5286","article-title":"Domain adaptive imitation learning","volume-title":"International Conference on Machine Learning","author":"Kim"},{"article-title":"State alignment-based imitation learning","year":"2019","author":"Liu","key":"ref18"},{"key":"ref19","article-title":"Playing hard exploration games by watching youtube","volume":"31","author":"Aytar","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71704-9_65"},{"key":"ref25","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"International conference on machine learning","author":"Ganin"},{"article-title":"Barnes-hut-sne","year":"2013","author":"Van Der Maaten","key":"ref26"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref27"},{"article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","year":"2021","author":"Yu","key":"ref28"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","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\/10651458.pdf?arnumber=10651458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:30:05Z","timestamp":1725949805000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651458","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}