TRPO algorithm

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 live online training, plus books, videos, and digital content from nearly 200 publishers.