{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:09:29Z","timestamp":1775189369628,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,21]]},"DOI":"10.1109\/cog57401.2023.10333147","type":"proceedings-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T18:48:21Z","timestamp":1701715701000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Sample Efficient Reinforcement Learning with Double Importance Sampling Weight Clipping"],"prefix":"10.1109","author":[{"given":"Jiale","family":"Han","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxiao","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bench-marking deep reinforcement learning for continuous control","volume-title":"ICML","author":"Duan"},{"key":"ref2","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref5","article-title":"Amber: Adaptive multi-batch experience replay for continuous action control","author":"Han","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848046"},{"key":"ref7","article-title":"Dimension-wise importance sampling weight clipping for sample-efficient reinforcement learning","volume-title":"ICML","author":"Han"},{"key":"ref8","article-title":"Generalized proximal policy optimization with sample reuse","author":"Queeney","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","article-title":"Trust region policy optimization","volume-title":"ICML","author":"Schulman"},{"key":"ref10","article-title":"Continuous control with deep reinforcement learning","volume-title":"ICLR","author":"Lillicrap"},{"key":"ref11","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"ICML","author":"Fujimoto"},{"key":"ref12","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"ICML","author":"Haarnoja"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref14","article-title":"Q-prop: Sample-efficient policy gradient with an off-policy critic","volume-title":"ICLR","author":"Gu"},{"key":"ref15","article-title":"Sample efficient actor-critic with experience replay","volume-title":"ICLR","author":"Wang"},{"key":"ref16","article-title":"P3o: Policy-on policy-off policy optimization","volume-title":"UAI","author":"Fakoor"},{"key":"ref17","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"ICLR","author":"Schulman"},{"key":"ref18","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"ICML","author":"Espeholt"},{"key":"ref19","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref20","article-title":"Box2d: A 2d physics engine for games","author":"Catto","year":"2011"},{"key":"ref21","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"ICML","author":"Mnih"},{"key":"ref22","article-title":"Openai baselines","author":"Dhariwal","year":"2017"},{"key":"ref23","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"Wu","year":"2017","journal-title":"NeurIPS"}],"event":{"name":"2023 IEEE Conference on Games (CoG)","location":"Boston, MA, USA","start":{"date-parts":[[2023,8,21]]},"end":{"date-parts":[[2023,8,24]]}},"container-title":["2023 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10333091\/10333129\/10333147.pdf?arnumber=10333147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:06:36Z","timestamp":1703030796000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10333147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cog57401.2023.10333147","relation":{},"subject":[],"published":{"date-parts":[[2023,8,21]]}}}