# Policy Gradient Optimization of Thompson Sampling Policies

arXiv: https://arxiv.org/abs/2006.16507 · HTML: https://mlsanity.com/paper/2006.16507/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

## Built on by (most cited first, 8 of 8)

- [Meta-Thompson Sampling](https://mlsanity.com/paper/2102.06129/) (2021)
- [No Regrets for Learning the Prior in Bandits](https://mlsanity.com/paper/2107.06196/) (2021)
- [Meta-Learning for Simple Regret Minimization](https://mlsanity.com/paper/2202.12888/) (2022)
- [Restless and Uncertain: Robust Policies for Restless Bandits via Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2107.01689/) (2021)
- [Adaptive Experimentation at Scale: A Computational Framework for Flexible Batches](https://mlsanity.com/paper/2303.11582/) (2023)
- [Advertising Media and Target Audience Optimization via High-dimensional Bandits](https://mlsanity.com/paper/2209.08403/) (2022)
- [Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits](https://mlsanity.com/paper/2408.15535/) (2024)
- [AExGym: Benchmarks and Environments for Adaptive Experimentation](https://mlsanity.com/paper/2408.04531/) (2024)

## Abstract (arXiv)

We study the use of policy gradient algorithms to optimize over a class of generalized Thompson sampling policies. Our central insight is to view the posterior parameter sampled by Thompson sampling as a kind of pseudo-action. Policy gradient methods can then be tractably applied to search over a class of sampling policies, which determine a probability distribution over pseudo-actions (i.e., sampled parameters) as a function of observed data. We also propose and compare policy gradient estimators that are specialized to Bayesian bandit problems. Numerical experiments demonstrate that direct policy search on top of Thompson sampling automatically corrects for some of the algorithm's known shortcomings and offers meaningful improvements even in long horizon problems where standard Thompson sampling is extremely effective.