6 papers
Expressivity and Statistical Trade-offs in Diffusion Policy Learning
Viet Vu, Renyuan Xu, Jiacheng Zhang +1
Diffusion-based policies have recently emerged as powerful policy parameterizations for reinforcement learning, representing state-conditioned action distributions as terminal laws…
Risk-Aware Linear Bandits: Theory and Applications in Smart Order Routing
Jingwei Ji, Renyuan Xu, Ruihao Zhu
Motivated by practical considerations in machine learning for financial decision-making, such as risk aversion and large action space, we consider risk-aware bandits optimization w…
Fast Policy Learning for Linear Quadratic Control with Entropy Regularization
Xin Guo, Xinyu Li, Renyuan Xu
This paper proposes and analyzes two new policy learning methods: regularized policy gradient (RPG) and iterative policy optimization (IPO), for a class of discounted linear-quadra…
Tail-GAN: Learning to Simulate Tail Risk Scenarios
Rama Cont, Mihai Cucuringu, Renyuan Xu +1
The estimation of loss distributions for dynamic portfolios requires the simulation of scenarios representing realistic joint dynamics of their components. We propose a novel data-…
Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators
Yinbin Han, Meisam Razaviyayn, Renyuan Xu
Nonlinear control systems with partial information to the decision maker are prevalent in a variety of applications. As a step toward studying such nonlinear systems, this work exp…
Model-free Analysis of Dynamic Trading Strategies
Anna Ananova, Rama Cont, Renyuan Xu
We introduce a model-free approach for analyzing the risk and return for a broad class of dynamic trading strategies, including pairs trading, mean-reversion trading and other stat…