BriefGPT.xyz
May, 2022
评论家顺序蒙特卡罗
Critic Sequential Monte Carlo
HTML
PDF
Vasileios Lioutas, Jonathan Wilder Lavington, Justice Sefas, Matthew Niedoba, Yunpeng Liu...
TL;DR
本文介绍了CriticSMC算法，结合学习的Soft-Q函数启发式因子实现了一种规划为推理的算法。实验表明该算法在高维仿真驾驶任务中显著降低了碰撞率，同时保持了较高的计算效率和真实性。
Abstract
We introduce
criticsmc
, a new algorithm for
planning
as inference built from a novel composition of sequential
monte carlo
with learned so
→