BriefGPT.xyz
Jan, 2024
具有有限重复次数的泛化嵌套展开策略调整
Generalized Nested Rollout Policy Adaptation with Limited Repetitions
HTML
PDF
Tristan Cazenave
TL;DR
通过限制特定层级上找到的最佳顺序的重复次数，我们改进了广义嵌套展开策略适应算法，从而避免了过于确定性的策略，实验证明这对于反向RNA折叠、旅行推销员问题和弱Schur问题这三个组合问题有所改进。
Abstract
generalized nested rollout policy adaptation
(GNRPA) is a
monte carlo search algorithm
for optimizing a sequence of choices. We propose to improve on GNRPA by avoiding too
→