A Bayesian oriented exploration and reinforcement learning in continuous-time mean-variance portfolio optimization
Abstract
We propose a new reinforcement learning (RL) framework for the continuous-time mean-variance portfolio optimization with unknown market parameters. To better reflect the impact of improved information of the unknown drift on the degree of exploration, we consider a novel randomization based on continuous-time stochastic filtering. Specifically, we construct a continuous-time analog to Thompson Sampling by treating the unknown drift as a random draw from a generalized sampling distribution parameterized by the filter's posterior mean and variance. The new learning objective measures the tradeoff between the wealth performance and the weighted KL divergence between the policy and the true Bayesian posterior, which transforms the classical feedback control into an information guided stochastic policy. As a result, the degree of exploration endogenously depends on the Reward-Biased Maximum Likelihood Estimation that decays with the shrinking filter's variance. This allows us to devise an efficient model-based learning algorithm in the mean-variance portfolio optimization with theoretical guarantee and superior learning performance.
Related
- Continuous-Time Mean-Variance Portfolio Selection Reinforcement Learning Problems for a Markov Regime-Switching System with No-Shorting Constraints
- Portfolio-Based Constrained Multi-Objective Bayesian Optimization for Materials Design
- Optimal Transport for Continuous-Time Mean-Variance Portfolio Selection
- Continuous-time q-Learning for Finite-Horizon Portfolio Choice with Optimal Stopping in Jump-Diffusion Markets
- Path-Space Robust Bayesian Portfolio Selection
BibTeX
@misc{chen2026bayesian,
title = {{A Bayesian oriented exploration and reinforcement learning in continuous-time mean-variance portfolio optimization}},
author = {Kexin Chen and Xiang Yu and Shanshan Zhao},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.10759},
eprint = {2611.10759},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.10759},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Bayesian oriented exploration and reinforcement learning in continuous-time mean-variance portfolio optimization
AU - Kexin Chen
AU - Xiang Yu
AU - Shanshan Zhao
PY - 2026
DA - 2026/11/07
PB - arXiv
DO - 10.48550/arxiv.2611.10759
UR - https://arxiv.org/abs/2611.10759
AB - We propose a new reinforcement learning (RL) framework for the continuous-time mean-variance portfolio optimization with unknown market parameters. To better reflect the impact of improved information of the unknown drift on the degree of exploration, we consider a novel randomization based on continuous-time stochastic filtering. Specifically, we construct a continuous-time analog to Thompson Sampling by treating the unknown drift as a random draw from a generalized sampling distribution parameterized by the filter's posterior mean and variance. The new learning objective measures the tradeoff between the wealth performance and the weighted KL divergence between the policy and the true Bayesian posterior, which transforms the classical feedback control into an information guided stochastic policy. As a result, the degree of exploration endogenously depends on the Reward-Biased Maximum Likelihood Estimation that decays with the shrinking filter's variance. This allows us to devise an efficient model-based learning algorithm in the mean-variance portfolio optimization with theoretical guarantee and superior learning performance.
ER -