Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Save more on your purchases now! discount-offer-chevron-icon
Savings automatically calculated. No voucher code required.
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Hands-On Reinforcement Learning for Games

You're reading from   Hands-On Reinforcement Learning for Games Implementing self-learning agents in games using artificial intelligence techniques

Arrow left icon
Product type Paperback
Published in Jan 2020
Publisher Packt
ISBN-13 9781839214936
Length 432 pages
Edition 1st Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
Micheal Lanham Micheal Lanham
Author Profile Icon Micheal Lanham
Micheal Lanham
Arrow right icon
View More author details
Toc

Table of Contents (19) Chapters Close

Preface 1. Section 1: Exploring the Environment
2. Understanding Rewards-Based Learning FREE CHAPTER 3. Dynamic Programming and the Bellman Equation 4. Monte Carlo Methods 5. Temporal Difference Learning 6. Exploring SARSA 7. Section 2: Exploiting the Knowledge
8. Going Deep with DQN 9. Going Deeper with DDQN 10. Policy Gradient Methods 11. Optimizing for Continuous Control 12. All about Rainbow DQN 13. Exploiting ML-Agents 14. DRL Frameworks 15. Section 3: Reward Yourself
16. 3D Worlds 17. From DRL to AGI 18. Other Books You May Enjoy

Summary

In this chapter, we introduced policy gradient methods, where we learned how to use a stochastic policy to drive our agent with the REINFORCE algorithm. After that, we learned that part of the problem of sampling from a stochastic policy is the randomness of sampling from a stochastic policy. We found that this could be corrected using dual agent networks, with one that represents the acting network and another as a critic. In this case, the actor is the policy network that refers back to the critic network, which uses a deterministic value function. Then, we saw how PG could be improved upon by seeing how DDPG works. Finally, we looked at what is considered one of the more complex methods in DRL, TRPO, and saw how it tries to manage the several shortcomings of PG methods.

Continuing with our look at PG methods, we will move on to explore next-generation methods such as...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime