{"id":4027,"date":"2023-11-17T06:22:00","date_gmt":"2023-11-16T21:22:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4027"},"modified":"2023-11-17T06:22:00","modified_gmt":"2023-11-16T21:22:00","slug":"%e5%bc%b7%e5%8c%96%e5%ad%a6%e7%bf%92%e3%81%a8%e6%8b%a1%e6%95%a3%e3%83%a2%e3%83%87%e3%83%ab","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4027","title":{"rendered":"\u5f37\u5316\u5b66\u7fd2\u3068\u62e1\u6563\u30e2\u30c7\u30eb"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Diffusion Models for Reinforcement Learning: A Survey&nbsp;<\/strong>[26.6]<br>\u62e1\u6563\u30e2\u30c7\u30eb\u306f\u3001\u751f\u6210\u30e2\u30c7\u30eb\u306e\u9855\u8457\u306a\u30af\u30e9\u30b9\u3068\u3057\u3066\u73fe\u308c\u3066\u3044\u308b\u3002 \u6700\u8fd1\u306e\u7814\u7a76\u306f\u3001\u5f37\u5316\u5b66\u7fd2\u30bd\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u306e\u6539\u5584\u306b\u304a\u3051\u308b\u62e1\u6563\u30e2\u30c7\u30eb\u306e\u5229\u70b9\u3092\u793a\u3057\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2311.01223v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2311.01223v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 2 Nov 2023 13:23:39 GMT)<\/li>\n\n\n\n<li>\u5f37\u5316\u5b66\u7fd2\u3068\u62e1\u6563\u30e2\u30c7\u30eb\u306b\u95a2\u3059\u308b\u30b5\u30fc\u30d9\u30a4\u3002\u62e1\u6563\u30e2\u30c7\u30eb\u306e\u5f79\u5272\u3068\u3057\u3066\u306f\u5927\u304d\u304f\u5206\u3051\u3066\u300cDiffusion models as the planner\u300d\u300cDiffusion models as the policy\u300d\u300cDiffusion models as the data synthesizer\u300d\u3068\u3044\u3046\u30a2\u30d7\u30ed\u30fc\u30c1\u304c\u3042\u308b\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/apexrl\/Diff4RLSurvey\">GitHub &#8211; apexrl\/Diff4RLSurvey: This repository contains a collection of resources and papers on Diffusion Models for RL, accompanying the paper &#8220;Diffusion Models for Reinforcement Learning: A Survey&#8221;<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[114,387,576],"class_list":["post-4027","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-diffusion-model","tag-survey","tag-576"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4027","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4027"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4027\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4027"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4027"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4027"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}