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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Traffic simulators are used to generate data for learning in intelligenttransportation systems (ITSs). A key question is to what extent their modellingassumptions affect the capabilities of ITSs to adapt to various scenarios whendeployed in the real world. This work focuses on two simulators commonly usedto train reinforcement learning (RL) agents for traffic applications, CityFlowand SUMO. A controlled virtual experiment varying driver behavior andsimulation scale finds evidence against distributional equivalence inRL-relevant measures from these simulators, with the root mean squared errorand KL divergence being significantly greater than 0 for all assessed measures.While granular real-world validation generally remains infeasible, thesefindings suggest that traffic simulators are not a deus ex machina for RLtraining: understanding the impacts of inter-simulator differences is necessaryto train and deploy RL-based ITSs.

Purpose in the Machine: Do Traffic Simulators Produce Distributionally Equivalent Outcomes for Reinforcement Learning Applications?