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

Multi-agent interaction is a fundamental aspect of autonomous driving in thereal world. Despite more than a decade of research and development, the problemof how to competently interact with diverse road users in diverse scenariosremains largely unsolved. Learning methods have much to offer towards solvingthis problem. But they require a realistic multi-agent simulator that generatesdiverse and competent driving interactions. To meet this need, we develop adedicated simulation platform called SMARTS (Scalable Multi-Agent RL TrainingSchool). SMARTS supports the training, accumulation, and use of diversebehavior models of road users. These are in turn used to create increasinglymore realistic and diverse interactions that enable deeper and broader researchon multi-agent interaction. In this paper, we describe the design goals ofSMARTS, explain its basic architecture and its key features, and illustrate itsuse through concrete multi-agent experiments on interactive scenarios. Weopen-source the SMARTS platform and the associated benchmark tasks andevaluation metrics to encourage and empower research on multi-agent learningfor autonomous driving. Our code is available athttps://github.com/huawei-noah/SMARTS.

SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving