This course covers the fundamentals of reinforcement learning, including exploration, exploitation, Markov Decision Processes, dynamic programming, model-free prediction and control, function approximation, deep reinforcement learning, policy gradients, actor critics, planning, and advanced topics in deep RL. The course also includes a brief tour of deep RL agents and a classic games case study. The teaching method involves a combination of lectures, case studies, and hands-on exercises. This course is intended for individuals interested in gaining a comprehensive understanding of reinforcement learning techniques and their applications.
Overview
Syllabus
Reinforcement Learning 1: Introduction to Reinforcement Learning.
Reinforcement Learning 2: Exploration and Exploitation.
Reinforcement Learning 3: Markov Decision Processes and Dynamic Programming.
Reinforcement Learning 4: Model-Free Prediction and Control.
Reinforcement Learning 5: Function Approximation and Deep Reinforcement Learning.
Reinforcement Learning 6: Policy Gradients and Actor Critics.
Reinforcement Learning 7: Planning and Models.
Reinforcement Learning 8: Advanced Topics in Deep RL.
Reinforcement Learning 9: A Brief Tour of Deep RL Agents.
Reinforcement Learning 10: Classic Games Case Study.
Taught by
DeepMind
