Deep RL Bootcamp Lecture 5: Natural Policy Gradients, TRPO, PPO

标签：lower   http   form   alt   sam   HERE   web   sample   uga   

https://statweb.stanford.edu/~owen/mc/Ch-var-is.pdf

 https://zhuanlan.zhihu.com/p/29934206

 blue curve is the lower bounded one

conjugate gradient to solve the optimization problem.

Fisher information matrix, natural policy gradient

To write down an optimization problem, we can solve more robustly with more sample efficiency to update policy

 But Lis Lpg is not constrained, so we use KL to ...

it‘s hard to choose beta

TRPO is much worse than A3C on imaging game, where PPO does better

see the slide: limitations of TRPO

Deep RL Bootcamp Lecture 5: Natural Policy Gradients, TRPO, PPO

标签：lower   http   form   alt   sam   HERE   web   sample   uga   

原文地址：https://www.cnblogs.com/ecoflex/p/8976876.html