{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:11:56Z","timestamp":1755216716231,"version":"3.43.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892464","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T15:56:04Z","timestamp":1664553364000},"page":"01-10","source":"Crossref","is-referenced-by-count":0,"title":["Few-Shot Image-to-Semantics Translation for Policy Transfer in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Rei","family":"Sato","sequence":"first","affiliation":[{"name":"Graduate School of Science and Technology, University of Tsukuba,Tsukuba,Japan"}]},{"given":"Kazuto","family":"Fukuchi","sequence":"additional","affiliation":[{"name":"University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan"}]},{"given":"Jun","family":"Sakuma","sequence":"additional","affiliation":[{"name":"University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan"}]},{"given":"Youhei","family":"Akimoto","sequence":"additional","affiliation":[{"name":"University of Tsukuba,Faculty of Engineering, Information and Systems,Tsukuba,Japan"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref32","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref31","article-title":"Diverse mini-batch active learning","author":"zhdanov","year":"2019","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.09.060"},{"key":"ref36","article-title":"Prox-imal policy optimization algorithms","volume":"1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning","year":"2016","author":"coumans","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"ref11","article-title":"Robust policies via mid-level visual representations: An experimental study in manipulation and navigation","author":"chen","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43089-4_44"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01117"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561157"},{"key":"ref16","article-title":"Modular deep q net-works for sim-to-real transfer of visuo-motor policies","author":"zhang","year":"0","journal-title":"Australasian Conference on Robotics and Automation (ACRA)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919870227"},{"key":"ref18","article-title":"Learning cross-domain correspondence for control with dynamics cycle-consistency","author":"zhang","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013582"},{"key":"ref28","first-page":"2063","article-title":"Transfer learning for related reinforce-ment learning tasks via image-to-image translation","author":"gamrian","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref3","first-page":"1461","article-title":"Robotic grasping using deep rein-forcement learning","author":"joshi","year":"0","journal-title":"IEEE International Conference on Automation Science and Engineering (CASE)"},{"key":"ref6","article-title":"Deepmind control suite","author":"tassa","year":"2018","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref5","article-title":"Is a good representation sufficient for sample efficient reinforcement learning?","author":"du","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref2","first-page":"4344","article-title":"Learning by playing - solving sparse reward tasks from scratch","author":"riedmiller","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref9","first-page":"1480","article-title":"DARLA: Improving zero-shot transfer in reinforcement learning","author":"higgins","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref1","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref20","first-page":"5639","article-title":"CURL: contrastive unsupervised representations for reinforcement learning","author":"srinivas","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref22","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","author":"agarwal","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref21","first-page":"32","article-title":"Towards governing agent's efficacy: Action-conditional beta-vae for deep transparent reinforcement learning","author":"yang","year":"0","journal-title":"Asian Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.006"},{"key":"ref23","first-page":"2451","article-title":"Recurrent world models facilitate policy evolution","author":"ha","year":"2018","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","first-page":"2962","article-title":"Adversarial discrimi-native domain adaptation","author":"tzeng","year":"0","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref25","article-title":"Driving pol-icy transfer via modularity and abstraction","author":"m\u00fcller","year":"0","journal-title":"Conference on Robot Learning (CoRL)"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892464.pdf?arnumber=9892464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T18:44:13Z","timestamp":1754333053000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892464","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}