35 citations · 132 across the 27 of their papers we have counts for
27 papers
Learning under Opponent Unawareness in Linear-Quadratic Stochastic Games
Dantong Chu, Xuefeng Gao, Yufei Zhang
As firms increasingly deploy machine learning for strategic decision-making, understanding algorithmic interactions has become central to operations research and economics. This pa…
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…
Convergence Rates of Time Discretization in Extended Mean Field Control
Christoph Reisinger, Wolfgang Stockinger, Maria Olympia Tsianni +1
Piecewise constant control approximation provides a practical framework for designing numerical schemes of continuous-time control problems. We analyze the accuracy of such approxi…
Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo
Matthieu Meunier, Christoph Reisinger, Yufei Zhang
Designing efficient learning algorithms with complexity guarantees for Markov decision processes (MDPs) with large or continuous state and action spaces remains a fundamental chall…
An Offline Learning Approach to Propagator Models
Eyal Neuman, Wolfgang Stockinger, Yufei Zhang
We consider an offline learning problem for an agent who first estimates an unknown price impact kernel from a static dataset, and then designs strategies to liquidate a risky asse…
A Neural RDE approach for continuous-time non-Markovian stochastic control problems
Melker Hoglund, Emilio Ferrucci, Camilo Hernandez +4
We propose a novel framework for solving continuous-time non-Markovian stochastic control problems by means of neural rough differential equations (Neural RDEs) introduced in Morri…
Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems
Michael Giegrich, Christoph Reisinger, Yufei Zhang
We study the global linear convergence of policy gradient (PG) methods for finite-horizon continuous-time exploratory linear-quadratic control (LQC) problems. The setting includes…
Decomposing User-APP Graph into Subgraphs for Effective APP and User Embedding Learning
Tan Yu, Jun Zhi, Yufei Zhang +3
APP-installation information is helpful to describe the user's characteristics. The users with similar APPs installed might share several common interests and behave similarly in s…
Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning
Lukasz Szpruch, Tanut Treetanthiploet, Yufei Zhang
This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms. Herein agent interacts…
Linear convergence of a policy gradient method for some finite horizon continuous time control problems
Christoph Reisinger, Wolfgang Stockinger, Yufei Zhang
Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamic…
Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models
Lukasz Szpruch, Tanut Treetanthiploet, Yufei Zhang
We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting. We then apply it to study finite-time horizon stochastic control prob…
A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems
Christoph Reisinger, Wolfgang Stockinger, Yufei Zhang
We propose a PDE-based accelerated gradient algorithm for optimal feedback controls of McKean-Vlasov dynamics that involve mean-field interactions both in the state and action. The…
Model Pruning Based on Quantified Similarity of Feature Maps
Zidu Wang, Xuexin Liu, Long Huang +4
Convolutional Neural Networks (CNNs) has been applied in numerous Internet of Things (IoT) devices for multifarious downstream tasks. However, with the increasing amount of data on…
Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls
Xin Guo, Anran Hu, Yufei Zhang
We study finite-time horizon continuous-time linear-convex reinforcement learning problems in an episodic setting. In this problem, the unknown linear jump-diffusion process is con…
Path regularity of coupled McKean-Vlasov FBSDEs
Christoph Reisinger, Wolfgang Stockinger, Yufei Zhang
This paper establishes Hölder time regularity of solutions to coupled McKean-Vlasov forward-backward stochastic differential equations (MV-FBSDEs). This is not only of fundamental…
Optimal regularity of extended mean field controls and their piecewise constant approximation
Christoph Reisinger, Wolfgang Stockinger, Yufei Zhang
We consider the control of McKean-Vlasov dynamics whose coefficients have mean field interactions in the state and control. We show that for a class of linear-convex mean field con…
A posteriori error estimates for fully coupled McKean-Vlasov forward-backward SDEs
Christoph Reisinger, Wolfgang Stockinger, Yufei Zhang
Fully coupled McKean-Vlasov forward-backward stochastic differential equations (MV-FBSDEs) arise naturally from large population optimization problems. Judging the quality of given…
Logarithmic regret for episodic continuous-time linear-quadratic reinforcement learning over a finite-time horizon
Matteo Basei, Xin Guo, Anran Hu +1
We study finite-time horizon continuous-time linear-quadratic reinforcement learning problems in an episodic setting, where both the state and control coefficients are unknown to t…
Understanding Deep Architectures with Reasoning Layer
Xinshi Chen, Yufei Zhang, Christoph Reisinger +1
Recently, there has been a surge of interest in combining deep learning models with reasoning in order to handle more sophisticated learning tasks. In many cases, a reasoning task…
Regularity and stability of feedback relaxed controls
Christoph Reisinger, Yufei Zhang
This paper proposes a relaxed control regularization with general exploration rewards to design robust feedback controls for multi-dimensional continuous-time stochastic exit time…
A neural network based policy iteration algorithm with global -superlinear convergence for stochastic games on domains
Kazufumi Ito, Christoph Reisinger, Yufei Zhang
In this work, we propose a class of numerical schemes for solving semilinear Hamilton-Jacobi-Bellman-Isaacs (HJBI) boundary value problems which arise naturally from exit time prob…
Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
Christoph Reisinger, Yufei Zhang
In this paper, we establish that for a wide class of controlled stochastic differential equations (SDEs) with stiff coefficients, the value functions of corresponding zero-sum game…
Error estimates of penalty schemes for quasi-variational inequalities arising from impulse control problems
Christoph Reisinger, Yufei Zhang
This paper proposes penalty schemes for a class of weakly coupled systems of Hamilton-Jacobi-Bellman quasi-variational inequalities (HJBQVIs) arising from stochastic hybrid control…
A penalty scheme for monotone systems with interconnected obstacles: convergence and error estimates
Christoph Reisinger, Yufei Zhang
We present a novel penalty approach for a class of quasi-variational inequalities (QVIs) involving monotone systems and interconnected obstacles. We show that for any given positiv…