Teaching · August 2021
Zinal Summer School 2021
Reinforcement learning lecture series · EPFL Summer School on Data Science, Optimization and Operations Research · Zinal, Switzerland
Overview
Niao He was honoured to be part of the EPFL Summer School 2021 on Data Science, Optimization and Operations Research in Zinal, Switzerland, together with Yurii Nesterov. Below is the agenda of her lecture series on reinforcement learning, with the slides of each lecture.
Lecture series
16 Aug 2021Lecture 1: Introduction to Reinforcement Learning
This lecture focuses on the fundamental concepts and challenges of RL.
17 Aug 2021Lecture 2: RL from Control Perspectives
This lecture focuses on the convergence analysis of value-based RL from unified dynamical-systems perspectives.
18 Aug 2021Lecture 3: RL from Optimization Perspectives
This lecture focuses on the global convergence analysis of policy-based RL from non-convex optimization perspectives.
19 Aug 2021Lecture 4: RL from Deep Learning Perspectives
This lecture focuses on the generalization and regularization of deep RL from deep-learning perspectives.
20 Aug 2021Lecture 5: RL from Game Perspectives
This lecture focuses on game perspectives of RL.