{"version":"1.0","blog_title":"\u30aa\u30e0\u30e9\u30a4\u30b9\u306e\u5099\u5fd8\u9332","width":"100%","author_url":"https://blog.hatena.ne.jp/yhayato1320/","provider_url":"https://hatena.blog","type":"rich","blog_url":"https://yhayato1320.hatenablog.com/","image_url":"https://docs.google.com/drawings/d/e/2PACX-1vQTSMrQHU4PNnkjYfOiyGmP97NhQM8BsIn5ao1Rpm4sTsKP3ETJPTsNqsIrIzIoGTlqLpi6L2JlnRWP/pub?w=765&h=560","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fyhayato1320.hatenablog.com%2Fentry%2F2023%2F02%2F24%2F174820\" title=\"\u3010\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u3011\u5f37\u5316\u5b66\u7fd2 / Reinforcement Learning - \u30aa\u30e0\u30e9\u30a4\u30b9\u306e\u5099\u5fd8\u9332\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","description":"Index Index Reinforcement Learning Reinforcement Learning from Human Feedback / RLHF \u30a2\u30eb\u30b4\u30ea\u30ba\u30e0 Interactive Textual Environment/ BabyAI-Text / 2023 Directional Stimulus Prompting / DSP / 2023 \u30e9\u30a4\u30d6\u30e9\u30ea TRL \u7814\u7a76 Reward Design with Language Models \u53c2\u8003 Reinforcement Learning Reinforcement Learning \u3092\u7528\u3044\u305f LLM \u306e\u6539\u5584. R\u2026","title":"\u3010\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u3011\u5f37\u5316\u5b66\u7fd2 / Reinforcement Learning","url":"https://yhayato1320.hatenablog.com/entry/2023/02/24/174820","categories":[],"author_name":"yhayato1320","provider_name":"Hatena Blog","height":"190","published":"2023-02-24 17:48:20"}