This paper proposes a method for policy learning called policy-vote bagging, which learns treatment decisions on many subsamples then averages their votes into treatment probabilities, which preserves expected welfare and improves expected utility for a risk-averse researcher.
Abstract
In evidence-based policymaking, typically one experimental sample is observed, then a learned policy recommendation is implemented at scale. Policies learned from the experimental data can perform well in expected welfare, yet random sampling in the experiment can produce recommendations with poor welfare outcomes. In this paper, we ask: how should policy learning algorithms balance expected welfare against sampling risk? Our main contribution is to show that algorithmic stability plays a central role in characterizing and navigating the tradeoff. Intuitively, if a policy learning algorithm's recommendation remains stable when one experimental unit is replaced, then that algorithm has limited sampling risk. We propose a method for policy learning called policy-vote bagging, which learns treatment decisions on many subsamples then averages their votes into treatment probabilities. Relative to using one subsample, averaging across subsamples preserves expected welfare and improves expected utility for a risk-averse researcher. We derive sharp bounds linking estimation accuracy, subsample size, and welfare variation, including an exact guarantee under CARA utility.
Reliable progress in offline policy learning depends on careful reporting, well-tuned baselines, and evaluation across diverse conditions. Prior work has shown that results can be sensitive to reporting choices, hyperparameter tuning, and dataset properties, but these sources of variability have not been systematically...
In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate this issue, behavior policy search has been proposed to learn data-collecting policies tailored to reduce online evaluation variance. However, these approaches do not ac...
Claire Chen, S. Liu, Licheng Luo et al.· 2 citations
Off-policy evaluation (OPE) for contextual bandit policies becomes challenging when action-level importance weighting incurs excessive variance. Doubly robust (DR) estimation remains unbiased under common support but retains these high-variance action-level weights. A prior estimator, Off-policy evaluation with Conjunc...
Nicolò Felicioni, Michael Benigni, Maurizio Ferrari Dacrema et al.· 0 citations
Policy learning methods based on conditional average treatment effects can obscure subpopulation heterogeneity when applied to ordinal outcomes. We develop a policy learning framework for ordinal outcomes with heterogeneous utilities for individuals who strictly benefit from treatment and those who do not. Since the pr...
This work introduces Minimal Intervention Reinforcement Learning (MInTRL), which expands the exploration frontier through sparse, local interventions in otherwise on-policy rollouts, and establishes minimal intervention as an effective paradigm for enhancing on-policy RL.
Ming-Yu Chen, Ye-Fan Tao, Gerald Friedland et al.· 1 citation
The results challenge the view that on-policy rollouts are inherently preferable and show that their value depends critically on the objective, evaluation setting, and optimisation hyperparameters.
Julianna Piskorz, Antonin Berthon, M. van der Schaar· arXiv.org· 1 citation
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 6, 2026
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.