Published inAI Learning NotesProximal Policy Optimization (PPO) in a NutshellProximal Policy Optimization (PPO) is one of the most popular and successful reinforcement learning (RL) algorithms used in many…Oct 5, 2024Oct 5, 2024
Published inAI Learning NotesTrust Region Methods Easy ExplanationTrust Region methods are optimization techniques used in reinforcement learning (RL) to ensure that policy updates are stable and don’t…Oct 5, 2024Oct 5, 2024
Published inAI Learning NotesPolicy Gradient in Reinforcement Learning Easy ExplanationPolicy Gradient methods are a class of reinforcement learning (RL) techniques where the policy (i.e., the strategy that tells an agent what…Oct 5, 2024Oct 5, 2024
Published inAI Learning NotesWhat is METEOR (Metric for Evaluation of Translation with Explicit ORdering)?METEOR is an evaluation metric for machine translation that improves over traditional metricsto to better align with human judgments.Sep 30, 2024Sep 30, 2024
Published in臨床心理學家的跨界漫遊之旅：人文、醫療、與科技社科博士轉職資料科學家的地獄之路（二）：履歷準備網路上的履歷教學很多，包括履歷格式、常見用詞、如何針對工作客製化等等應該都能輕易查到，但今天我想從「看的人」的角度出發來思考怎麼寫履歷。Sep 14, 2023Sep 14, 2023
Published in臨床心理學家的跨界漫遊之旅：人文、醫療、與科技文組博士轉職資料科學家的地獄之路（一）：求職背景與心態先回答一個常見問題：「臨床心理學是文組嗎？」Sep 11, 2023Sep 11, 2023
