English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we focus on the autonomous multiagent taxi routing problem fora large urban environment where the location and number of future ride requestsare unknown a-priori, but follow an estimated empirical distribution. Recenttheory has shown that if a base policy is stable then a rollout-based algorithmwith such a base policy produces a near-optimal stable policy. Although,rollout-based approaches are well-suited for learning cooperative multiagentpolicies with considerations for future demand, applying such methods to alarge urban environment can be computationally expensive. Large environmentstend to have a large volume of requests, and hence require a large fleet oftaxis to guarantee stability. In this paper, we aim to address thecomputational bottleneck of multiagent (one-at-a-time) rollout, where thecomputational complexity grows linearly in the number of agents. We propose anapproximate one-at-a-time rollout-based two-phase algorithm that reduces thecomputational cost, while still achieving a stable near-optimal policy. Ourapproach partitions the graph into sectors based on the predicted demand and anuser-defined maximum number of agents that can be planned for using theone-at-a-time rollout approach. The algorithm then applies instantaneousassignment (IA) for re-balancing taxis across sectors and a sector-wideone-at-a-time rollout algorithm that is executed in parallel for each sector.We characterize the number of taxis $m$ that is sufficient for IA base policyto be stable, and derive a necessary condition on $m$ as time goes to infinity.Our numerical results show that our approach achieves stability for an $m$ thatsatisfies the theoretical conditions. We also empirically demonstrate that ourproposed two-phase algorithm has comparable performance to the one-at-a-timerollout over the entire map, but with significantly lower runtimes.

Approximate Multiagent Reinforcement Learning for On-Demand Urban Mobility Problem on a Large Map (extended version)