AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification

Connor Thomas Jerzak, Priyanshi Chandra, Rishi Hazra

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 1 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
average-case optimal stochastic interventionSynthetic binary conjoint · learn a factored stochastic policy instead of per-factor AMCE maximizersexpected outcomeImproved
average-case optimizerSynthetic binary conjoint · increase sample size nRMSE of policy and valueImproved
minimax policy learning2016 US presidential conjoint (Ono & Burden) · use adversarial restricted-equilibrium optimizer instead of average-case optimizerimplied two-party vote shareImproved
adversarial minimax policyAdversarial simulation (R vs D primaries) · increase sample size n from 1000 to larger95% CI coverageImproved
adversarial minimax policyAdversarial simulation · vary proportion of Republican votersestimation errorNo clear effect
policy learningSynthetic misspecification study · use Bayesian Transformer instead of GLM outcome model under strong nonlinear misspecificationRMSE and coverageMixed
policy learningSynthetic misspecification study · use GLM with pairwise interactions when linear approximation holdsefficiency and calibrationImproved

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