UCL Course on RL

Advanced Topics  2015 (COMPM050/COMPGI13)

Reinforcement Learning

Contact: d.silver@cs.ucl.ac.uk

Video-lectures available here

Lecture 1: Introduction to Reinforcement Learning

Lecture 2: Markov Decision Processes

Lecture 3: Planning by Dynamic Programming

Lecture 4: Model-Free Prediction

Lecture 5: Model-Free Control

Lecture 6: Value Function Approximation

Lecture 7: Policy Gradient Methods

Lecture 8: Integrating Learning and Planning

Lecture 9: Exploration and Exploitation

Lecture 10: Case Study: RL in Classic Games

Easy21 assignment

Discussion and announcements: http://groups.google.com/group/csml-advanced-topics

Previous RL exam questions and answers