课程定位
RL 理论、探索、函数逼近与前沿方向综述。 本页保留官方档案与入口,具体内容与考核以当季官网为准。
主要内容
本页为延伸课程速览,主要内容见下方官方描述。
先修
见官方描述(延伸课程暂未单独整理先修)。
考核与工作量
以当季官网为准(延伸课程暂未单独整理考核)。
适合谁
对「高级强化学习」方向感兴趣的人。
学习建议
先读官方描述和课程官网,再判断是否适合自己。
相关课程
官方课程描述(英文原文)
This class will provide a core overview of essential topics and new research frontiers in reinforcement learning. Planned topics include: model free and model based reinforcement learning, policy search, Monte Carlo Tree Search planning methods, off policy evaluation, exploration, imitation learning, temporal abstraction/hierarchical approaches, safety and risk sensitivity, human-in-the-loop RL, inverse reinforcement learning, learning to communicate, and insights from human learning. Students are expected to create an original research paper on a related topic. Prerequisites: CS 221 or AA 238/CS 238 or CS 234 or CS 229 or similar experience.