IJCAIJun, 2018
组织体验:对连续状态领域基于样本规划的回放机制的深入探讨
Organizing Experience: A Deeper Look at Replay Mechanisms for Sample-based Planning in Continuous State Domains
Yangchen Pan, Muhammad Zaheer, Adam White, Andrew Patterson, Martha White
TL;DR本文介绍了一种基于模型的规划策略,使用 REWEIGHTED EXPERIENCE MODELS 方法实现了对 Dyna planning paradigm 的重新定义,在连续状态问题上取得了比回放 buffer 更好的表现。