Distributed Online Rollout for Multivehicle Routing in Unmapped Environments
Jamison W. Weber, Dhanush R. Giriyan, Devendra R. Parkar, Dimitri P., Bertsekas, Andr\'ea W. Richa

TL;DR
This paper introduces a distributed reinforcement learning algorithm for multivehicle routing in unknown environments, enabling agents with local sensing to self-organize and improve routing efficiency without centralized control.
Contribution
It presents a novel fully distributed, online reinforcement learning approach that allows multiagent systems to coordinate locally and improve routing costs in unknown environments.
Findings
Distributed rollout improves over greedy policy beyond a critical sensing radius.
Critical sensing radius scales logarithmically with network size.
Algorithm achieves approximately double the cost efficiency of the base policy.
Abstract
In this work we consider a generalization of the well-known multivehicle routing problem: given a network, a set of agents occupying a subset of its nodes, and a set of tasks, we seek a minimum cost sequence of movements subject to the constraint that each task is visited by some agent at least once. The classical version of this problem assumes a central computational server that observes the entire state of the system perfectly and directs individual agents according to a centralized control scheme. In contrast, we assume that there is no centralized server and that each agent is an individual processor with no a priori knowledge of the underlying network (including task and agent locations). Moreover, our agents possess strictly local communication and sensing capabilities (restricted to a fixed radius around their respective locations), aligning more closely with several real-world…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsOptimization and Search Problems · Distributed Control Multi-Agent Systems · Reinforcement Learning in Robotics
MethodsBalanced Selection
