A Friendly Introduction to Deep Reinforcement Learning, Q-Networks and Policy Gradients
Offered By: Serrano.Academy via YouTube
Course Description
Overview
Explore deep reinforcement learning, Q-networks, and policy gradients in this friendly 36-minute video tutorial. Dive into key concepts such as Markov decision processes, rewards, discount factors, and the Bellman equation. Learn about deterministic and stochastic processes before delving into neural networks, including value and policy networks. Understand how to train policy neural networks and gain insights through examples and figures. Perfect for those with a basic understanding of neural networks, this comprehensive guide covers everything from introduction to conclusion, offering a solid foundation in reinforcement learning techniques.
Syllabus
Introduction:
Markov decision processes MDP:
Rewards:
Discount factor:
Bellman equation:
Solving the Bellman equation:
Deterministic vs stochastic processes:
Neural networks:
Value neural networks:
Policy neural networks:
Training the policy neural network:
Conclusion:
Taught by
Serrano.Academy
Related Courses
Neural Networks for Machine LearningUniversity of Toronto via Coursera 機器學習技法 (Machine Learning Techniques)
National Taiwan University via Coursera Machine Learning Capstone: An Intelligent Application with Deep Learning
University of Washington via Coursera Прикладные задачи анализа данных
Moscow Institute of Physics and Technology via Coursera Leading Ambitious Teaching and Learning
Microsoft via edX