Главная
Study mode:
on
1
Introduction:
2
Markov decision processes MDP:
3
Rewards:
4
Discount factor:
5
Bellman equation:
6
Solving the Bellman equation:
7
Deterministic vs stochastic processes:
8
Neural networks:
9
Value neural networks:
10
Policy neural networks:
11
Training the policy neural network:
12
Conclusion:
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it 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.

A Friendly Introduction to Deep Reinforcement Learning, Q-Networks and Policy Gradients

Serrano.Academy
Add to list
0:00 / 0:00