{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:51:54Z","timestamp":1780512714941,"version":"3.54.1"},"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":8,"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Dong","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Sun","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Song","sequence":"additional","affiliation":[{"name":"Hefei Institute of Physical Science, CAS,Institute of Intelligent Machines,Hefei,China,230031"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"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"},{"key":"ref8","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref10","article-title":"Decoupling dynamics and reward for transfer learning","author":"Zhang","year":"2018"},{"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"},{"key":"ref16","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.10.011"},{"key":"ref18","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017"},{"key":"ref19","first-page":"16 828","article-title":"The primacy bias in deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Nikishin"},{"key":"ref20","article-title":"Learning abstract models for strategic exploration and fast reward transfer","author":"Liu","year":"2020"},{"key":"ref21","article-title":"Understanding and preventing capacity loss in reinforcement learning","author":"Lyle","year":"2022"},{"key":"ref22","article-title":"Continual back-prop: Stochastic gradient descent with persistent randomness","author":"Dohare","year":"2021"},{"key":"ref23","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref24","article-title":"Reincarnating reinforcement learning: Reusing prior computation to accelerate progress","author":"Agarwal","year":"2022"},{"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"},{"key":"ref26","article-title":"Openai gym","author":"Brockman","year":"2016"},{"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"},{"key":"ref29","article-title":"Relay hindsight experience replay: Continual reinforcement learning for robot manipulation tasks with sparse rewards","author":"Luo","year":"2022"},{"key":"ref30","article-title":"Exploiting reward shifting in value-based deep rl","author":"Sun","year":"2022"}],"event":{"name":"2023 IEEE International Conference on Real-time Computing and Robotics (RCAR)","location":"Datong, China","start":{"date-parts":[[2023,7,17]]},"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]]}}}