20
Black-Box Optimization in RL
In this chapter, we will change our perspective on reinforcement learning (RL) training again and switch to the so-called black-box optimizations. In particular, this chapter will cover two examples of black-box optimization methods:
- Evolution strategies
- Genetic algorithms
These methods are at least a decade old, but recently, several research studies were conducted that showed the applicability of the methods to large-scale RL problems, and their competitiveness with the value iteration and policy gradient methods.
Black-box methods
To begin with, let's discuss the whole family of black-box methods and how it differs from what we've covered so far. Black-box optimization methods are the general approach to ...
Get Deep Reinforcement Learning Hands-On - Second Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
