Gatekeeper: A deep reinforcement learning-cum-heuristic based algorithm for scheduling and routing trains in complex environments

The problem of optimal and efficient scheduling and navigation of trains in large railway networks has attracted attention from both operations research (OR) and artificial intelligence (AI) communities. At its core, this problem is comprised of two inter-linked sub-problems: the vehicle re-scheduling problem (VRSP) and the multi-agent path-finding problem (MAPF). In this paper, we propose Gatekeeper: a reinforcement-learning-cum-heuristic based approach for scheduling and path planning of trains in complex environments. By extensive experiments on the Flatland (a public customisable environment for multi-train scheduling and path planning), we show that Gatekeeper outperforms top RL baselines both in terms of normalized scores and makespan, while remaining competitive against pure heuristic algorithms.