A stochastic process approach for multi-agent path finding with non-asymptotic performance guarantees

DOI10.1016/J.ARTINT.2024.104084WikidataQ128901159 ScholiaQ128901159MaRDI QIDQ6494378

Xiaoyu He, Jingning Li, Wentong Cai, Xueyan Tang

Publication date: 30 April 2024

Published in: Artificial Intelligence (Search for Journal in Brave)

zbMATH Keywords

stochastic processmulti-armed bandit problemnon-asymptotic performancemulti-agent path finding

Mathematics Subject Classification ID

Multi-objective and goal programming (90C29) Inference from stochastic processes (62M99) Agent technology and artificial intelligence (68T42)

Cites Work

• Anytime Pareto local search
• The increasing cost tree search for optimal multi-agent pathfinding
• A survey of some simulation-based algorithms for Markov decision processes
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Conflict-based search for optimal multi-agent pathfinding
• Heuristic search viewed as path finding in a graph
• Introduction to Multi-Armed Bandits
• Benchmarking optimization software with performance profiles.
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: A stochastic process approach for multi-agent path finding with non-asymptotic performance guarantees