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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| average-case optimal stochastic intervention | Synthetic binary conjoint · learn a factored stochastic policy instead of per-factor AMCE maximizers | expected outcome | Improved |
| average-case optimizer | Synthetic binary conjoint · increase sample size n | RMSE of policy and value | Improved |
| minimax policy learning | 2016 US presidential conjoint (Ono & Burden) · use adversarial restricted-equilibrium optimizer instead of average-case optimizer | implied two-party vote share | Improved |
| adversarial minimax policy | Adversarial simulation (R vs D primaries) · increase sample size n from 1000 to larger | 95% CI coverage | Improved |
| adversarial minimax policy | Adversarial simulation · vary proportion of Republican voters | estimation error | No clear effect |
| policy learning | Synthetic misspecification study · use Bayesian Transformer instead of GLM outcome model under strong nonlinear misspecification | RMSE and coverage | Mixed |
| policy learning | Synthetic misspecification study · use GLM with pairwise interactions when linear approximation holds | efficiency and calibration | Improved |
Closest papers by meaning
- A Minimaximalist Approach to Reinforcement Learning from Human Feedback (ICML 2024 · similarity 0.87)
- Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning (ICLR 2025 · similarity 0.86)
- Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning (NeurIPS 2024 · similarity 0.86)
- Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer (NeurIPS 2024 · similarity 0.86)
- Understanding Model Selection for Learning in Strategic Environments (NeurIPS 2024 · similarity 0.85)
- Adversarial Causal Bayesian Optimization (ICLR 2024 · similarity 0.85)
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.
