dose the linesearch method conflict with a "trust region" policy gradient algorithm?

[nuomizai]

Hi, I am a newcomer to drl. When I try to read trpo_step in trpo.py, I notice that you use a linesearch method instead of trust region for numerical optimization. So I want to know why you choose that method and dose it conflict with a "trust region" policy gradient algorithm?

[ArtificialIntelligenceRobot]

I think u can read the paper for more information, you question is explaned at appendix c