Advances in Stochastic Control and Reinforcement Learning
Videos from BIRS Workshop
Csaba Szepesvári, University of Alberta
Monday Apr 28, 2025 09:06 - 10:02
Foundations and Frontiers in Reinforcement Learning Theory
Christoph Reisinger, University of Oxford
Monday Apr 28, 2025 10:35 - 11:04
Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo
Jose Blanchet, Stanford
Monday Apr 28, 2025 11:10 - 11:38
Wasserstein Distributionally Robust Regret Optimization
David Siska, University of Edinburgh
Monday Apr 28, 2025 13:01 - 13:41
Entropy Annealing for Policy Mirror Descent in Continuous Time and Space
Renyuan Xu, New York University
Monday Apr 28, 2025 15:06 - 15:36
Stochastic Control for Fine-Tuning Diffusion Models: Optimality, Regularity, and Convergence
Serdar Yuksel, Queen's University
Tuesday Apr 29, 2025 09:02 - 09:34
Stochastic Kernel Topologies on Models and Policies: Implications for Approximations, Robustness and Learning
Gergely Neu, Universitat Pompeu Fabra
Tuesday Apr 29, 2025 10:31 - 11:03
Optimal Transport Distances for Markov Chains
Ben Hambly, University of Oxford
Tuesday Apr 29, 2025 12:58 - 13:38
Systemic Risk, Endogenous Contagion and Mean Field Control
Sebastian Jaimungal, University of Toronto
Tuesday Apr 29, 2025 14:28 - 15:03
Broker-Trader Partial Information Nash Equilibria
Leandro Sánchez-Betancourt, University of Oxford
Tuesday Apr 29, 2025 15:03 - 15:29
Market Making with Exogenous Competition
Samuel Cohen, University of Oxford
Tuesday Apr 29, 2025 15:29 - 16:07
Bayesian Opimal Adaptive Control
Ruimeng Hu, University of California, Santa Barbara
Wednesday Apr 30, 2025 09:12 - 09:33
A Mean Field Analysis of Climate Change Uncertainty
Mathieu Lauriere, NYU Shanghai
Wednesday Apr 30, 2025 09:34 - 10:09
A Simulation-Free Deep Learning Approach to Stochastic Optimal Control
Yuhua Zhu, UCLA
Wednesday Apr 30, 2025 10:33 - 11:03
Optimal PhiBE — A Model-Free PDE-Based Framework for Continuous-Time RL
Dena Firoozi, HEC Montréal - Université de Montréal
Thursday May 1, 2025 09:35 - 10:07
Infinite-Dimensional LQ Mean Field Games
Clemens Possnig, University of Waterloo
Thursday May 1, 2025 10:34 - 11:06
Strategic Communication and Algorithmic Advice
Jiacheng Zhang, Chinese University of Hong Kong
Thursday May 1, 2025 13:02 - 13:37
Minimax-Optimal Trust-Aware Multi-Armed Bandits
