YoVDO

Fundamentals of Deep Reinforcement Learning

Offered By: Learn Ventures via edX

Tags

Deep Learning Courses Neural Networks Courses Markov Decision Processes Courses Dynamic programming Courses Deep Reinforcement Learning Courses Q-learning Courses Bellman Equations Courses

Course Description

Overview

This course starts from the very beginnings of Reinforcement Learning and works its way up to a complete understanding of Q-learning, one of the core reinforcement learning algorithms.

In part II of this course, you'll use neural networks to implement Q-learning to produce powerful and effective learning agents (neural nets are the "Deep" in "Deep Reinforcement Learning").


Syllabus

  • Introduction to Reinforcment Learning
  • Bandit Problems
    • Epsilon Greedy Agent
  • Markov Decision Processes
    • Episode Returns
    • Returns and Discount Factors
  • The Bellman Equation
  • Iterative Policy Evaluation and Improvement
  • Policy Evaluation and Iteration
  • Dynamic Programming
  • Q-Learning and Sampling Based Methods
  • Monte Carlo Rollouts vs. Temporal Difference Learning
  • On-Policy Learning vs. Off-Policy Learning
  • Q-Learning
  • What's Next

Taught by

Xander Steenbrugge, Frank Washburn and Shalev NessAiver

Related Courses

Reinforcement Learning
Edureka Deep Reinforcement Learning
Nvidia Deep Learning Institute via Udacity A Friendly Introduction to Deep Reinforcement Learning, Q-Networks and Policy Gradients
Serrano.Academy via YouTube Nonconvex Homogenization for 1D Controlled Brownian Motion in a Random Potential
Institute for Pure & Applied Mathematics (IPAM) via YouTube Intro to Artificial Intelligence - Markov Decision Process (MDP) - Lecture 17
Dave Churchill via YouTube