使用图神经网络驱动的蒙特卡洛树搜索求解带机会约束的随机定向越野问题
Solving Stochastic Orienteering Problems with Chance Constraints Using a GNN Powered Monte Carlo Tree Search
AI总结：
本文提出一种图神经网络驱动的蒙特卡洛树搜索方法，通过GNN加速rollout阶段并预测动作效用与失败概率，高效求解带机会约束的随机定向越野问题，实验证明其能高效求解复杂实例并具备泛化能力。
摘要：
利用具有消息传递机制的图神经网络（GNN）的能力，我们提出了一种蒙特卡洛树搜索（MCTS）方法，用于求解带机会约束的随机定向越野问题。在遵守指定旅行预算的同时，该算法在产生随机旅行成本的情况下寻求最大化收集到的奖励。在此背景下，超出指定预算的可接受概率被表达为机会约束。我们的MCTS解决方案是一种在线且随时可用的算法，交替进行规划与执行，通过持续监测剩余旅行预算来确定下一个要访问的顶点。我们工作的新颖之处在于，MCTS框架中的 rollout 阶段使用消息传递GNN实现，同时预测每个可用动作的效用和失败概率。这使得搜索过程得以极大加速。我们的实验评估表明，利用所提出的方法和架构，我们能够高效求解复杂问题实例，同时在收集奖励方面仅产生适度损失。此外，我们证明了该方法能够泛化到训练数据集特征之外的情形。本文的网站、开源代码和补充文档可在 ucmercedrobotics.github.io/gnn-sop 找到。
英文摘要：
Leveraging the power of a graph neural network (GNN) with message passing, we present a Monte Carlo Tree Search (MCTS) method to solve stochastic orienteering problems with chance constraints. While adhering to an assigned travel budget the algorithm seeks to maximize collected reward while incurring stochastic travel costs. In this context, the acceptable probability of exceeding the assigned budget is expressed as a chance constraint. Our MCTS solution is an online and anytime algorithm alternating planning and execution that determines the next vertex to visit by continuously monitoring the remaining travel budget. The novelty of our work is that the rollout phase in the MCTS framework is implemented using a message passing GNN, predicting both the utility and failure probability of each available action. This allows to enormously expedite the search process. Our experimental evaluation shows that with the proposed method and architecture we manage to efficiently solve complex problem instances while incurring in moderate losses in terms of collected reward. Moreover, we demonstrate how the approach is capable of generalizing beyond the characteristics of the training dataset. The paper's website, open-source code, and supplementary documentation can be found at ucmercedrobotics.github.io/gnn-sop.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
