AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control

Afshin Oroojlooy, Mohammadreza Nazari, Davood Hajinezhad, Jorge Silva

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 39 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Train one policy across multiple intersection environments instead of training a separate policy per intersectionAttendLight · Training instancesATT: 15% ATT degradationHurt
Train one policy across multiple intersection environments instead of training a separate policy per intersectionAttendLight · Testing instances unseen during trainingATT: 13% ATT gap with a standard deviation of 0.19Mixed
Fine-tune the universal policy for an individual intersectionAttendLight multi-env · Specialized intersectionATT gap versus single-env: 5% gap on averageImproved
Continue fine-tuning the universal policy for an individual intersectionAttendLight multi-env · Specialized intersectionATT gap versus single-env: 3%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy