MDPO

2000년 도입 · 논문 4편에서 사용

Mirror Descent Policy Optimization (MDPO) is a policy gradient algorithm based on the idea of iteratively solving a trust-region problem that minimizes a sum of two terms: a linearization of the standard RL objective function and a proximity term that restricts two consecutive updates to be close to each other. It is based on Mirror Descent, which is a general trust region method that attempts to keep consecutive iterates close to each other.

출처: Mirror Descent Policy Optimization

소개 논문: Mirror Descent Policy Optimization