paper-with-me

Ape-X DPG

2000년 도입 · 논문 1편에서 사용

Ape-X DPG combines DDPG with distributed prioritized experience replay through the Ape-X architecture.

출처: Distributed Prioritized Experience Replay

소개 논문: Distributed Prioritized Experience Replay

Policy Gradient Methods · Reinforcement Learning