{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T09:00:07Z","timestamp":1767085207030,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T00:00:00Z","timestamp":1689552000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T00:00:00Z","timestamp":1689552000000},"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":[[2023,7,17]]},"DOI":"10.1109\/rcar58764.2023.10249999","type":"proceedings-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T17:36:59Z","timestamp":1695231419000},"page":"906-911","source":"Crossref","is-referenced-by-count":7,"title":["D2SR: Transferring Dense Reward Function to Sparse by Network Resetting"],"prefix":"10.1109","author":[{"given":"Yongle","family":"Luo","sequence":"first","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}]},{"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}]},{"given":"Kun","family":"Dong","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}]},{"given":"Zhiyong","family":"Sun","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}]},{"given":"Bo","family":"Song","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192770"},{"key":"ref4","first-page":"5048","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"article-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"Fujimoto","key":"ref8"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref9"},{"article-title":"Decoupling dynamics and reward for transfer learning","year":"2018","author":"Zhang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/AIM52237.2022.9863259"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00068"},{"article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","year":"2018","author":"Plappert","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.10.011"},{"article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","year":"2017","author":"Vecerik","key":"ref18"},{"key":"ref19","first-page":"16 828","article-title":"The primacy bias in deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Nikishin"},{"article-title":"Learning abstract models for strategic exploration and fast reward transfer","year":"2020","author":"Liu","key":"ref20"},{"article-title":"Understanding and preventing capacity loss in reinforcement learning","year":"2022","author":"Lyle","key":"ref21"},{"article-title":"Continual back-prop: Stochastic gradient descent with persistent randomness","year":"2021","author":"Dohare","key":"ref22"},{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Haarnoja","key":"ref23"},{"article-title":"Reincarnating reinforcement learning: Reusing prior computation to accelerate progress","year":"2022","author":"Agarwal","key":"ref24"},{"key":"ref25","article-title":"When to use parametric models in reinforcement learning?","volume":"32","author":"Van Hasselt","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Openai gym","year":"2016","author":"Brockman","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.02.090"},{"article-title":"Relay hindsight experience replay: Continual reinforcement learning for robot manipulation tasks with sparse rewards","year":"2022","author":"Luo","key":"ref29"},{"article-title":"Exploiting reward shifting in value-based deep rl","year":"2022","author":"Sun","key":"ref30"}],"event":{"name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","start":{"date-parts":[[2023,7,17]]},"location":"Datong, China","end":{"date-parts":[[2023,7,20]]}},"container-title":["2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10249208\/10249018\/10249999.pdf?arnumber=10249999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:09:23Z","timestamp":1710403763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10249999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,17]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/rcar58764.2023.10249999","relation":{},"subject":[],"published":{"date-parts":[[2023,7,17]]}}}