Главная
Study mode:
on
1
Intro
2
Learning in Dynamic Environments
3
Classes of Learning Problems
4
Reinforcement Learning (RL): Key Concepts
5
Defining the Q-function
6
Deep Reinforcement Learning Algorithms
7
Digging deeper into the Q-function
8
Deep Q Network Summary
9
Downsides of Q-learning
10
Discrete vs Continuous Action Spaces
11
Policy Gradient (PG): Key Idea
12
Training Policy Gradients: Case Study
13
Reinforcement Learning in Real Life
14
Reinforcement Learning and the Game of Go
15
Deep Reinforcement Learning Summary
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore deep reinforcement learning in this comprehensive lecture from MIT's Introduction to Deep Learning course. Delve into key concepts of reinforcement learning, including dynamic environments, Q-functions, and policy gradients. Learn about deep Q networks, their advantages and limitations, and the differences between discrete and continuous action spaces. Discover real-life applications of reinforcement learning, including its role in mastering the game of Go. Gain insights from case studies and practical examples presented by lecturer Alexander Amini. Perfect for those seeking to understand the fundamentals and advanced topics in deep reinforcement learning.

MIT: Reinforcement Learning

Alexander Amini
Add to list
#Computer Science #Machine Learning #Reinforcement Learning #Deep Reinforcement Learning #Policy Gradient #Deep Q Networks
1 of 15

Intro