Jump in. It's gonna be fun!
Course Objectives
01
Foundations of RL methods: value/policy iteration, q-learning, policy gradient, etc. - with math & batteries included
02
Using deep neural networks for RL tasks - also known as "the hype train"
03
State of the art RL algorithms - and how to apply duct tape to them for practical problems
04
Teaching your neural network to play games - because that's what everyone thinks RL is about
Learning Outcomes
1. Learn how to solve reinforcement learning problems with stochastic optimization methods
2. Apply the dynamic programming to Markov Decision process at hand
3. Know the difference between on-policy and off-policy learning algorithms
4. Practice in implementing RL algorithms with function approximation
Course Syllabus
Week 1. Intro: why should I care?
Week 2. At the heart of RL: Dynamic Programming
Week 3. Model-free methods
Week 4. Approximate Value Based Methods
Week 5. Policy-based methods
Week 6. Exploration
Teachers
Researcher at HSE Faculty of Computer Science and Sberbank AI Lab
Lecturer: HSE Faculty of Computer Science
Learning Activities
Lectures
Online
Low-Stakes Assignments
Tests
High-Stakes Assignments
Final project
Cost and Conditions
16 000 ₽
Full access to the learning materials + Graduation document
More: публичная оферта