演講時間: 113年9月25日（三） 14:00~16:00

演講地點: E6-A207教室

演講者: 吳毅成 教授（國立陽明交通大學 資訊工程學系）

演講主題: 深度強化式學習與其應用：從電腦對局到製造最佳化與大語言模型

講題大綱：In this talk, I first introduce Deep Reinforcement Learning (DRL), one of the key AI technologies and one of the three machine learning paradigms. Google's DeepMind developed a Go program, AlphaGo, that defeat the Go champion, which was thought to be not possible to happen within one or two decades. Then, present the ongoing researches on DRL applications from computer games to Manufacturing Optimization and Large Language Model. Particularly, present the application from DRL to the large language model, so called RLHF (reinforcement learning from human feedback) and RLAIF (reinforcement learning from AI feedback).

請研究所一年級的同學當天準時聽講