https://kcsgoodboy.github.io/ko/activities.html 2026-06-18T00:44:43.526Z https://kcsgoodboy.github.io/ko/projects/data-driven-rl-washing-machines/index.html 2026-06-18T00:44:43.650Z https://kcsgoodboy.github.io/ko/publications.html 2026-06-18T00:44:43.657Z https://kcsgoodboy.github.io/ko/posts/2026-03-19-RL_for_LLMs_Preference_Optimization/post.html 2026-06-18T00:44:43.627Z https://kcsgoodboy.github.io/ko/posts/2026-01-23_Transfer_learning/post.html 2026-06-18T00:44:43.573Z https://kcsgoodboy.github.io/ko/posts/2026-02-23-Offline_RL/post.html 2026-06-18T00:44:43.613Z https://kcsgoodboy.github.io/ko/posts/2026-01-20_Multi-task_learning/post.html 2026-06-18T00:44:43.567Z https://kcsgoodboy.github.io/ko/posts/2025-07-28_taylor_expansion/post.html 2026-06-18T00:44:43.529Z https://kcsgoodboy.github.io/ko/posts/2026-03-24-Model_Based_RL/post.html 2026-06-18T00:44:43.637Z https://kcsgoodboy.github.io/ko/posts/2026-03-10-Reward_Learning/post.html 2026-06-18T00:44:43.623Z https://kcsgoodboy.github.io/ko/posts/2026-02-03_Off_Policy_Actor_Critic_Methods/post.html 2026-06-18T00:44:43.591Z https://kcsgoodboy.github.io/ko/index.html 2026-06-18T00:44:43.529Z https://kcsgoodboy.github.io/ko/blog.html 2026-06-18T00:44:43.526Z https://kcsgoodboy.github.io/ko/posts/2026-01-28_Actor_Critic_Methods/post.html 2026-06-18T00:44:43.578Z https://kcsgoodboy.github.io/ko/posts/2025-07-31_Vibe_Coding_Success_Fail/post.html 2026-06-18T00:44:43.530Z https://kcsgoodboy.github.io/ko/posts/2026-02-02_Black_Box_Meta_Learning/post.html 2026-06-18T00:44:43.586Z https://kcsgoodboy.github.io/ko/posts/2025-08-14_Introduction_to_On_Device_AI/post.ko.html 2026-06-18T00:44:43.562Z https://kcsgoodboy.github.io/ko/posts/2026-02-20_Non_Parametric_Few_Shot_Learning/post.html 2026-06-18T00:44:43.608Z https://kcsgoodboy.github.io/ko/posts/2025-08-07_Particle_Tachyon_Unboxing/post.html 2026-06-18T00:44:43.536Z https://kcsgoodboy.github.io/ko/posts/2026-02-10_Q_Learning/post.html 2026-06-18T00:44:43.602Z https://kcsgoodboy.github.io/ko/posts/2026-02-09_Optimization_Based_Meta_Learning/post.html 2026-06-18T00:44:43.597Z https://kcsgoodboy.github.io/ko/posts/2025-12-29_retrospective_of_2025/post.html 2026-06-18T00:44:43.567Z https://kcsgoodboy.github.io/ko/about.html 2026-06-18T00:44:43.526Z https://kcsgoodboy.github.io/ko/projects/reward-learning-dryer/index.html 2026-06-18T00:44:43.657Z https://kcsgoodboy.github.io/activities.html 2026-06-18T00:43:57.984Z https://kcsgoodboy.github.io/projects/data-driven-rl-washing-machines/index.html 2026-06-18T00:43:58.111Z https://kcsgoodboy.github.io/publications.html 2026-06-18T00:43:58.119Z https://kcsgoodboy.github.io/posts/2026-03-19-RL_for_LLMs_Preference_Optimization/post.html 2026-06-18T00:43:58.089Z https://kcsgoodboy.github.io/posts/2026-01-23_Transfer_learning/post.html 2026-06-18T00:43:58.034Z https://kcsgoodboy.github.io/posts/2026-02-23-Offline_RL/post.html 2026-06-18T00:43:58.074Z https://kcsgoodboy.github.io/posts/2026-02-20_Non_Parametric_Few_Shot_Learning/post.html 2026-06-18T00:43:58.069Z https://kcsgoodboy.github.io/posts/2025-08-14_Introduction_to_On_Device_AI/post.ko.html 2026-06-18T00:43:58.023Z https://kcsgoodboy.github.io/posts/2026-02-02_Black_Box_Meta_Learning/post.html 2026-06-18T00:43:58.047Z https://kcsgoodboy.github.io/posts/2025-07-31_Vibe_Coding_Success_Fail/post.html 2026-06-18T00:43:57.988Z https://kcsgoodboy.github.io/posts/2026-01-28_Actor_Critic_Methods/post.html 2026-06-18T00:43:58.039Z https://kcsgoodboy.github.io/blog.html 2026-06-18T00:43:57.985Z https://kcsgoodboy.github.io/index.html 2026-06-18T00:43:57.988Z https://kcsgoodboy.github.io/posts/2026-02-03_Off_Policy_Actor_Critic_Methods/post.html 2026-06-18T00:43:58.052Z https://kcsgoodboy.github.io/posts/2026-03-10-Reward_Learning/post.html 2026-06-18T00:43:58.084Z https://kcsgoodboy.github.io/posts/2026-03-24-Model_Based_RL/post.html 2026-06-18T00:43:58.098Z https://kcsgoodboy.github.io/posts/2025-07-28_taylor_expansion/post.html 2026-06-18T00:43:57.988Z https://kcsgoodboy.github.io/posts/2026-01-20_Multi-task_learning/post.html 2026-06-18T00:43:58.028Z https://kcsgoodboy.github.io/posts/2026-02-10_Q_Learning/post.html 2026-06-18T00:43:58.063Z https://kcsgoodboy.github.io/posts/2026-02-09_Optimization_Based_Meta_Learning/post.html 2026-06-18T00:43:58.058Z https://kcsgoodboy.github.io/posts/2025-12-29_retrospective_of_2025/post.html 2026-06-18T00:43:58.027Z https://kcsgoodboy.github.io/about.html 2026-06-18T00:43:57.984Z https://kcsgoodboy.github.io/projects/reward-learning-dryer/index.html 2026-06-18T00:43:58.119Z