提出两种安全的抽象消退策略，提升MCTS搜索效率与性能。
Time-critical and confidence-based abstraction dropping methods
- 基于时间与置信度设计动态抽象消退机制
- 两种方法在相同迭代下均显著提升MCTS表现
- 适用于对实时性或收敛性有要求的强化学习场景
蒙特卡洛树搜索（MCTS）的一种改进范式是在搜索过程中构建并使用状态和/或动作抽象。然而，非精确抽象会引入近似误差，导致无法收敛到抽象空间中的最优动作。因此，如Xu等人提出的弹性蒙特卡洛树搜索中所述，抽象算法最终应放弃抽象。本文提出两种新颖的抽象消退方案——OGA-IAAD与OGA-CAD，可在保证安全的前提下实现明显性能提升，其消退过程不会造成显著性能下降，与Xu的方法相反。OGA-IAAD专为时间敏感场景设计，而OGA-CAD则旨在相同迭代次数下优化MCTS性能。
原文摘要 · Abstract (English)
One paradigm of Monte Carlo Tree Search (MCTS) improvements is to build and use state and/or action abstractions during the tree search. Non-exact abstractions, however, introduce an approximation error making convergence to the optimal action in the abstract space impossible. Hence, as proposed as a component of Elastic Monte Carlo Tree Search by Xu et al., abstraction algorithms should eventually drop the abstraction. In this paper, we propose two novel abstraction dropping schemes, namely OGA-IAAD and OGA-CAD which can yield clear performance improvements whilst being safe in the sense that the dropping never causes any notable performance degradations contrary to Xu's dropping method. OGA-IAAD is designed for time critical settings while OGA-CAD is designed to improve the MCTS performance with the same number of iterations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。