An α-potential game framework for N-player games (with Xin Guo and Xinyu Li) (2024) [Preprint]
Mirror descent for stochastic control problems with measure-valued controls (with Bekzhan Kerimkulov, David Siska and Lukasz Szpruch) Submitted (2024) [Preprint]
A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces (with Bekzhan Kerimkulov, James-Michael Leahy, David Siska and Lukasz Szpruch) Submitted (2023) [Preprint]
Towards An Analytical Framework for Potential Games (with Xin Guo) Submitted (2023) [Preprint]
An offline learning approach to propagator models (with Eyal Neuman and Wolfgang Stockinger) Submitted (2023) [Preprint] [Colab Notebook]
Insurance pricing on price comparison websites via reinforcement learning (with Tanut Treetanthiploet, Lukasz Szpruch, Isaac Bowers-Barnard, Henrietta Ridley, James Hickey and Chris Pearce) (2023) [Preprint]
Statistical learning with sublinear regret of propagator models (with Eyal Neuman) Submitted (2023) [Preprint]
A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems (with Christoph Reisinger and Wolfgang Stockinger) Revision requested from SIAM Journal on Scientific Computing (2021) [Preprint]
Path regularity of coupled McKean-Vlasov FBSDEs (with Christoph Reisinger and Wolfgang Stockinger) (2020) [Preprint]
Optimal regularity of extended mean field controls and their piecewise constant approximation (with Christoph Reisinger and Wolfgang Stockinger) (2020) [Preprint]
Refereed journal publications
Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models (with Lukasz Szpruch and Tanut Treetanthiploet) The Annals of Applied Probability, forthcoming (2024) [Preprint]
Convergence of policy gradient methods for finite-horizon stochastic linear-quadratic control problems (with Michael Giegrich and Christoph Reisinger) SIAM Journal on Control and Optimization, 62 (2024), pp. 1060-1092 [pdf] [Preprint]
Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning (with Lukasz Szpruch and Tanut Treetanthiploet) SIAM Journal on Control and Optimization, 62 (2024), pp. 135-166 [pdf] [Preprint]
Linear convergence of a policy gradient method for some finite horizon continuous time control problems (with Christoph Reisinger and Wolfgang Stockinger) SIAM Journal on Control and Optimization, 61 (2023), pp. 3526-3558 [pdf] [Preprint]
A posteriori error estimates for fully coupled McKean-Vlasov forward-backward SDEs (with Christoph Reisinger and Wolfgang Stockinger) IMA Journal of Numerical Analysis, forthcoming, 2023 [Preprint]
Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls (with Xin Guo and Anran Hu) SIAM Journal on Control and Optimization, 61 (2023), pp. 755-787 [pdf] [Preprint]
Logarithmic regret for episodic continuous-time linear-quadratic reinforcement learning over a finite-time horizon (with Matteo Basei, Xin Guo and Anran Hu) Journal of Machine Learning Research, 23 (2022), pp. 1–34 [pdf] [Preprint]
Regularity and stability of feedback relaxed controls (with Christoph Reisinger) SIAM Journal on Control and Optimization, 59 (2021), pp. 3118–3151 [pdf] [Preprint]
A penalty scheme and policy iteration for non-local HJB variational inequalities with monotone drivers (with Christoph Reisinger) Computers and Mathematics with Applications, 93 (2021), pp. 199-213 [pdf] [Preprint]
Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems (with Christoph Reisinger) Analysis and Applications, 18 (2020), pp. 951-999 [Preprint]
A neural network based policy iteration algorithm with global $H^2$-superlinear convergence for stochastic games on domains (with Kazufumi Ito and Christoph Reisinger) Foundations of Computational Mathematics, 21 (2021), pp. 331–374 [pdf]
Error estimates of penalty schemes for quasi-variational inequalities arising from impulse control problems (with Christoph Reisinger) SIAM Journal on Control and Optimization, 58 (2020), pp. 243-276 [pdf]
A penalty scheme for monotone systems with interconnected obstacles: convergence and error estimates (with Christoph Reisinger) SIAM Journal of Numerical Analysis, 57 (2019), pp. 1625-1648 [pdf]
Approximation schemes for mixed optimal stopping and control problems with nonlinear expectations and jumps (with Roxana Dumitrescu and Christoph Reisinger) Applied Mathematics & Optimization, 83 (2021), pp. 1387–1429 [pdf]
Refereed conference publications
Understanding Deep Architectures with Reasoning Layer (with Xinshi Chen, Christoph Reisinger and Le Song) Advances in Neural Information Processing Systems (NeurIPS), 2020. [Preprint]