Skip to Main Content
Deep Reinforcement Learning Hands-On
book

Deep Reinforcement Learning Hands-On

by Oleg Vasilev, Maxim Lapan, Martijn van Otterlo, Mikhail Yurushkin, Basem O. F. Alijla
June 2018
Intermediate to advanced content levelIntermediate to advanced
546 pages
13h 30m
English
Packt Publishing
Content preview from Deep Reinforcement Learning Hands-On

Trust Region Policy Optimization

TRPO was proposed in 2015 by the Berkeley researchers in the paper by John Schulman et al called Trust Region Policy Optimization (arXiv:1502.05477). This paper was a step towards improving the stability and consistency of the stochastic policy gradient optimization and has shown good results on various control tasks.

Unfortunately, the paper and the method are quite math-heavy, so it can be hard to understand the details of the method. The same could be said about the implementation, which uses the conjugate gradients method to efficiently solve the constrained optimization problem.

As the first step, the TRPO method defines the discounted visitation frequencies of the state: . In this equation, equals to the sampled ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Grokking Deep Reinforcement Learning

Grokking Deep Reinforcement Learning

Miguel Morales

Publisher Resources

ISBN: 9781788834247Supplemental Content