# General Bayesian Policy Learning

arXiv: https://arxiv.org/abs/2602.23672 · HTML: https://mlsanity.com/paper/2602.23672/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 58 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 18 of 18)

- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [User-friendly introduction to PAC-Bayes bounds](https://mlsanity.com/paper/2110.11216/) (2021)
- [A General Framework for Updating Belief Distributions](https://mlsanity.com/paper/1306.6430/) (2013)
- [On the properties of variational approximations of Gibbs posteriors](https://mlsanity.com/paper/1506.04091/) (2015)
- [Offline Multi-Action Policy Learning: Generalization and Optimization](https://mlsanity.com/paper/1810.04778/) (2018)
- [Assigning a value to a power likelihood in a general Bayesian model](https://mlsanity.com/paper/1701.08515/) (2017)
- [End to end learning and optimization on graphs](https://mlsanity.com/paper/1905.13732/) (2019)
- [PAC-Bayes unleashed: generalisation bounds with unbounded losses](https://mlsanity.com/paper/2006.07279/) (2020)
- [General Bayesian Updating and the Loss-Likelihood Bootstrap](https://mlsanity.com/paper/1709.07616/) (2017)
- [Bayesian Counterfactual Risk Minimization](https://mlsanity.com/paper/1806.11500/) (2018)
- [Calibrating general posterior credible regions](https://mlsanity.com/paper/1509.00922/) (2015)
- [Fast Rates for General Unbounded Loss Functions: from ERM to Generalized Bayes](https://mlsanity.com/paper/1605.00252/) (2016)
- [A comparison of learning rate selection methods in generalized Bayesian inference](https://mlsanity.com/paper/2012.11349/) (2020)
- [PAC-Bayesian Offline Contextual Bandits With Guarantees](https://mlsanity.com/paper/2210.13132/) (2022)
- [Bayesian Predictive Decision Synthesis](https://mlsanity.com/paper/2206.03815/) (2022)
- [Predictive Decision Synthesis for Portfolios: Betting on Better Models](https://mlsanity.com/paper/2405.01598/) (2024)
- [Bayesian Portfolio Optimization by Predictive Synthesis](https://mlsanity.com/paper/2510.07180/) (2025)

## Abstract (arXiv)

This study proposes a General Bayes framework for policy learning. We consider decision problems in which a decision-maker chooses an action from a given set to maximize expected welfare. Typical examples include treatment choice and portfolio optimization. In such problems, the statistical target is a decision rule, and predicting each potential outcome is not necessarily of primary interest. We formulate this policy-learning problem through loss-based Bayesian updating. Our main technical device is a squared-loss surrogate for welfare maximization. We show that maximizing empirical welfare over a policy class with a quadratic penalty controlled by a tuning parameter zeta>0 is equivalent to minimizing a scaled squared error in the outcome difference. The resulting General Bayes posterior over decision rules admits two equivalent characterizations: a Gaussian pseudo-likelihood representation and a decision-theoretic loss-based characterization. As one implementation, we introduce GBPLNet, a neural network implementation with a tanh-squashed output. Finally, we establish PAC-Bayes-type guarantees for the surrogate risk and the corresponding penalized welfare.