AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Stateful Strategic Regression

Keegan Harris, Hoda Heidari, Steven Wu

NeurIPS 2021 · Multi-agent systems and games › Games and equilibria · approach: Strategic classification · 0 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
Extend the interaction from one round to multiple rounds with effort accumulation in an internal stateStateful strategic regression · Principal-agent effort incentivesrange of incentivizable effort profilesImproved
Allow studying effort to accumulate as knowledge over timeTeacher-student example · Classroom exampleincentivized effortImproved
Use linear assessment policies instead of the broader class of monotonic policiesStateful strategic regression · Effort-policy incentivizabilityset of incentivizable effort policiesNo clear effect
Assume a linear effort conversion functionEquilibrium computation · Stateful strategic regressionequilibrium computation tractabilityImproved
Replace the fixed per-round effort budget with a quadratic effort cost (ablation)Stateful strategic regression · Equilibrium propertiesqualitative findingsNo clear effect
Increase the time horizon when a desired effort component accumulates faster than competing componentsStateful strategic regression · Effort implementabilityimplementability of the desired effortImproved

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