Based on the preceding policy improvement bound, the following algorithm is developed:
Initialize policy;Repeat for each step
: Compute all advantage values
; Solve the following optimization problem:
;Until convergence
In each step, this algorithm minimizes the upper bound of , so that:
The last equation follows from that for any ...
Get Python Reinforcement Learning Projects 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.
Get Mark Richards’s Software Architecture Patterns ebook to better understand how to design components—and how they should interact.
Dive in for free with a 10-day trial of the O’Reilly learning platform—then explore all the other resources our members count on to build skills and solve problems every day.
Start your free trial Become a member now