主 讲 人：美国圣塔克拉拉大学陆海兵教授

讲座地点：6号学院楼402会议室

讲座时间： 7月2日早上8:30-11：00.

    7月3日早上8:30-11：00.

    7月4日早上8:30-11：00，下午14:00-16:30.

    7月5日早上8:30-11：00，下午14:00-16:30.

讲座内容：

Reinforcement learning (RL) is a framework for modeling an autonomous agent’s interaction with an unknown world. The agent’s objective is to learn the effects of its actions, and modify its policy in order to maximize future reward. The study of reinforcement learning emphasizes a learning approach to artificial intelligence. Unlike supervised learning, the agent is not explicitly told the correct answers (labels), rather an RL agent must learn only from reward and trial and error interaction with the world. This general framework has been used to optimize helicopter flight, schedule elevators, and achieve super-human level performance in many games (e.g., Backgammon, GO, and Atari). Ideas from reinforcement learning has also be used to explain learning in animals, and model dopamine activity in the human brain.

The objective of this seminar is to provide an introduction to some of the foundational ideas on which modern reinforcement learning is built, including Markov decision processes, value functions, Monte Carlo estimation, dynamic programming, temporal difference learning, eligibility traces, and function approximation. This seminar will develop an intuitive understanding of these concepts (taking the agent’s perspective), while also focusing on the mathematical theory of reinforcement learning.

Tentative Schedule

• Introduction to Reinforcement Learning

• Markov Decision Processes

• Planning by Dynamic Programming

• Model-Free Prediction

• Model-Free Control

• Value Function Approximation

• Policy Gradient Methods

• Integrating Learning and Planning

• Exploration and Exploitation

• Case Study: RL in Classic Game

Recommended Textbooks

• Reinforcement Learning: An Introduction, by Richard S. Sutton and Andrew G. Barto

• Algorithms for Reinforcement learning, by Csaba Szepesvari

主讲人简介：

陆海兵教授现任圣塔克拉拉大学运营管理和信息系统系的系主任，主要研究方向是大数据挖掘分析和信息安全。在国际顶级期刊和会议上发表了近50篇高引用率的论文。包括IEEE Transaction on Dependable and Security Computing , INFORMS Journal on Computing, Journal of Computer Security, IEEE Symposium on Security and Privacy, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIAM International Conference on Data Mining, IEEE International Conference on Data Mining, 和IEEE International Conference on Data Engineering。

欢迎感兴趣的师生积极参加！