{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T05:17:01Z","timestamp":1737004621150,"version":"3.33.0"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00397400,RS-2024-00421129"],"award-info":[{"award-number":["RS-2024-00397400,RS-2024-00421129"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007053","name":"Korea Institute of Energy Technology Evaluation and Planning","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007053","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"DOI":"10.1109\/ictc62082.2024.10827048","type":"proceedings-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:40:10Z","timestamp":1736883610000},"page":"653-655","source":"Crossref","is-referenced-by-count":0,"title":["Offline Goal-Conditioned Model-Based Reinforcement Learning in Pixel-Based Environment"],"prefix":"10.1109","author":[{"given":"Seongsu","family":"Kim","sequence":"first","affiliation":[{"name":"Hanyang University,Dept. Electrical Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Moon","sequence":"additional","affiliation":[{"name":"Hanyang University,Dept. Electrical Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Temporal difference learning for model predictive control","volume-title":"International Conference on Machine Learning (ICML)","author":"Hansen","year":"2022"},{"key":"ref2","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kostrikov","year":"2022"},{"key":"ref3","article-title":"Universal value function approximators","volume-title":"International Conference on Machine Learning (ICML)","author":"Schaul","year":"2015"},{"key":"ref4","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref5","article-title":"Contrastive learning as goal-conditioned reinforcement learning","author":"Eysenbach","year":"2022","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","article-title":"Hiql: Offline Goal-conditioned rl with latent states as actions","author":"Seohong","year":"2024","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref7","volume":"abs\/1910.00177","author":"Peng","year":"2019","journal-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning"},{"key":"ref8","article-title":"A policy-guided imitation approach for offline reinforcement learning","author":"Xu","year":"2022","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref9","article-title":"Isaac Gym: High performance gpu-based physics simulation for robot learning","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Makoviychuk","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","volume":"abs\/1607.06450","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref12","volume":"abs\/180.308375","author":"Agarap","year":"2018","journal-title":"Deep learning using rectified linear units (relu)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"}],"event":{"name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2024,10,16]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 15th International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10826571\/10826594\/10827048.pdf?arnumber=10827048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T07:01:59Z","timestamp":1736924519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10827048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/ictc62082.2024.10827048","relation":{},"subject":[],"published":{"date-parts":[[2024,10,16]]}}}