AI RESEARCH

Generalized Policy Gradient with History-Aware Decision Transformer for Reliable Routing over Graph Signals

arXiv CS.AI

ArXi:2508.17218v3 Announce Type: replace-cross Reliable path planning in stochastic transportation networks requires decisions that account for uncertain and correlated travel times on irregular road graphs, rather than only minimizing expected delay. Such networks exhibit strong spatial-temporal coupling, where link travel times evolve as stochastic processes over graph edges, making the problem inherently sequential under uncertainty.