{"id":3952,"date":"2023-10-24T05:47:00","date_gmt":"2023-10-23T20:47:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3952"},"modified":"2023-10-24T05:47:00","modified_gmt":"2023-10-23T20:47:00","slug":"eureka-evolution-driven-universal-reward-kit-for-agent","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3952","title":{"rendered":"EUREKA: \u00a0Evolution-driven Universal REward Kit for Agent"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Eureka: Human-Level Reward Design via Coding Large Language Models&nbsp;<\/strong>[126.0]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306f\u3001\u30b7\u30fc\u30b1\u30f3\u30b7\u30e3\u30eb\u306a\u610f\u601d\u6c7a\u5b9a\u30bf\u30b9\u30af\u306e\u305f\u3081\u306e\u30cf\u30a4\u30ec\u30d9\u30eb\u306a\u30bb\u30de\u30f3\u30c6\u30a3\u30c3\u30af\u30d7\u30e9\u30f3\u30ca\u30fc\u3068\u3057\u3066\u512a\u308c\u3066\u3044\u307e\u3059\u3002 LLM\u3092\u7528\u3044\u305f\u4eba\u9593\u30ec\u30d9\u30eb\u306e\u5831\u916c\u8a2d\u8a08\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3067\u3042\u308bEureka\u3092\u63d0\u6848\u3059\u308b\u3002 Eureka\u306f\u3001\u6700\u5148\u7aef\u306eLLM\u306e\u76ee\u899a\u307e\u3057\u3044\u30bc\u30ed\u30b7\u30e7\u30c3\u30c8\u751f\u6210\u3001\u30b3\u30fc\u30c9\u66f8\u304d\u3001\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u5185\u6539\u5584\u6a5f\u80fd\u3092\u5229\u7528\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2310.12931v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2310.12931v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 19 Oct 2023 17:31:01 GMT)<\/li>\n\n\n\n<li>LLM\u3092\u7528\u3044\u305f&nbsp;reward design algorithm&nbsp;\u306e\u63d0\u6848\u3002\u6027\u80fd\u306f\u4eba\u9593\u30ec\u30d9\u30eb\u3068\u306e\u3053\u3068\u3067\u3042\u308a\u3001\u300cEUREKA can improve and benefit from human reward functions.\u300d\u3068\u306e\u3053\u3068\u3002\u5f37\u5316\u5b66\u7fd2\u3092\u5229\u7528\u3059\u308b\u5834\u5408\u306b\u96e3\u3057\u3044\u90e8\u5206\u3092\u30b5\u30dd\u30fc\u30c8\u3067\u304d\u308b\u53ef\u80fd\u6027\u304c\u3042\u308b\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/eureka-research.github.io\/\">Eureka | Human-Level Reward Design via Coding Large Language Models (eureka-research.github.io)<\/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":[223,576],"class_list":["post-3952","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-576"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3952","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=3952"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3952\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3952"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3952"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3952"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}