Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning
在铺设道路之前击败路径:样本高效的蒙特卡洛规划
机构 * SequeL team, INRIA Lille - Nord Europe(SequeL团队,INRIA里尔-北欧分校) ; Google DeepMind(谷歌DeepMind)
AI总结 本文提出TrailBlazer算法,通过高效样本探索近优状态结构,实现样本效率高的蒙特卡洛规划,兼顾策略优化与计算效率。
Comments Published in Neural Information Processing Systems 2016