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

We introduce Nocturne, a new 2D driving simulator for investigatingmulti-agent coordination under partial observability. The focus of Nocturne isto enable research into inference and theory of mind in real-world multi-agentsettings without the computational overhead of computer vision and featureextraction from images. Agents in this simulator only observe an obstructedview of the scene, mimicking human visual sensing constraints. Unlike existingbenchmarks that are bottlenecked by rendering human-like observations directlyusing a camera input, Nocturne uses efficient intersection methods to compute avectorized set of visible features in a C++ back-end, allowing the simulator torun at over 2000 steps-per-second. Using open-source trajectory and map data,we construct a simulator to load and replay arbitrary trajectories and scenesfrom real-world driving data. Using this environment, we benchmarkreinforcement-learning and imitation-learning agents and demonstrate that theagents are quite far from human-level coordination ability and deviatesignificantly from the expert trajectories.

Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world