提出首个可并行化且保证策略优化的MCTS算法，提升推理效率。
PMCTS: Particle Monte Carlo Tree Search for Principled Parallelized Inference Time Scaling
- 将粒子滤波思想融入MCTS，实现并行搜索
- 在多个任务上显著优于现有启发式方法
- 适合需要高效推理的神经网络应用
蒙特卡洛树搜索（MCTS）是一种广泛用于策略改进的搜索方法，在现实应用中日益流行。由于其搜索过程具有顺序性和确定性，利用并行计算进行运行时扩展仍是重大挑战。我们提出粒子蒙特卡洛树搜索（PMCTS），据我们所知，这是首个理论上合理且适用于神经网络评估的并行化MCTS算法，同时能保持形式化的策略改进保证。实验表明，PMCTS在并行计算下表现良好，跨多个领域显著优于流行的基于启发式的基线方法。
原文摘要 · Abstract (English)
Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement through search with increasing popularity for real world applications. Due to the sequential and deterministic nature of its search, runtime-scaling of MCTS with parallel compute remains a major challenge. We introduce Particle MCTS (PMCTS), to our knowledge the first principled parallel MCTS algorithm which is suited for neural network evaluations and can preserve formal policy improvement guarantees. Empirically, PMCTS scales well with parallel compute and significantly outperforms the popular heuristic-based baselines across domains.
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。