# Risk-Constrained Thompson Sampling for CVaR Bandits

arXiv: https://arxiv.org/abs/2011.08046 · HTML: https://mlsanity.com/paper/2011.08046/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2020.

## Built on by (most cited first, 10 of 10)

- [Off-Policy Risk Assessment in Contextual Bandits](https://mlsanity.com/paper/2104.08977/) (2021)
- [Almost Optimal Variance-Constrained Best Arm Identification](https://mlsanity.com/paper/2201.10142/) (2022)
- [A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits](https://mlsanity.com/paper/2108.11345/) (2021)
- [Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget](https://mlsanity.com/paper/2211.14768/) (2022)
- [Off-Policy Risk Assessment in Markov Decision Processes](https://mlsanity.com/paper/2209.10444/) (2022)
- [Thompson Sampling for Gaussian Entropic Risk Bandits](https://mlsanity.com/paper/2105.06960/) (2021)
- [Conditionally Risk-Averse Contextual Bandits](https://mlsanity.com/paper/2210.13573/) (2022)
- [Risk averse non-stationary multi-armed bandits](https://mlsanity.com/paper/2109.13977/) (2021)
- [Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs](https://mlsanity.com/paper/2206.12463/) (2022)
- [Order Optimal Regret Bounds for Sharpe Ratio Optimization under Thompson Sampling](https://mlsanity.com/paper/2508.13749/) (2025)

## Abstract (arXiv)

The multi-armed bandit (MAB) problem is a ubiquitous decision-making problem that exemplifies the exploration-exploitation tradeoff. Standard formulations exclude risk in decision making. Risk notably complicates the basic reward-maximising objective, in part because there is no universally agreed definition of it. In this paper, we consider a popular risk measure in quantitative finance known as the Conditional Value at Risk (CVaR). We explore the performance of a Thompson Sampling-based algorithm CVaR-TS under this risk measure. We provide comprehensive comparisons between our regret bounds with state-of-the-art L/UCB-based algorithms in comparable settings and demonstrate their clear improvement in performance. We also include numerical simulations to empirically verify that CVaR-TS outperforms other L/UCB-based algorithms.