Organizing Committee
Comité d’organisation
Jean-françois Chassagneux (ENSAE-CREST & IP Paris)
Céline Labart (Université Savoie Mont-Blanc)
Marie-Amélie Morlais (Le Mans université)
Alexandre Popier (Le Mans université)
Adrien Richou (Université de Bordeaux)
The international closing conference of the ANR ReLISCoP project (Reinforcement learning for impulse stochastic control problem) is dedicated to new advances in the areas addressed by the ReLISCoP project: stochastic control problems (including optimal switching and mean-field problems) from theory to applications, model incertainty, reinforcement learning methods, probabilistic numerical methods. Leading international experts as well as members of the ANR project will present and share their latest advances in those fields.
La conférence internationale de clôture du projet ANR ReLISCoP (Reinforcement learning for impulse stochastic control problem) est dédiée aux nouvelles avancées dans les domaines abordés par le projet ReLISCoP : problèmes de contrôle stochastique (y compris les problèmes de commutation optimale et de champ moyen) de la théorie aux applications, incertitude des modèles, méthodes d’apprentissage par renforcement, méthodes numériques probabilistes. Des experts et expertes internationaux de premier plan ainsi que des membres du projet ANR présenteront et partageront leurs dernières avancées dans ces domaines.
SPEAKERS
Camilo Andres Garcia Trillos (University College London) Deep Learning Beyond Markov: FBSVIEs and Time-Inconsistent Control
Zakaria Bensaid (Le Mans Université) Deep learning algorithms for FBSDEs with jumps
Guillaume Broux-quemerais (Le Mans Université) Deep numerical schemes for systems of ergodic BSDEs with applications to regime-switching forward utilities
Sören Christensen (Kiel University) On Nonparametric Approaches to Data-Driven Stochastic Control
Giovanni Conforti (University of Padova) Convergence bounds for diffusion flow matching and iterative Markovian fitting procedure
Kaplan Desbouis (Institut de Mathématiques de Bordeaux) Probabilistic approach to mean-field ergodic control problems
Anna De Crescenzo (ETH Zurich) Mean-field control of heterogeneous systems
Hannah Geiss (University of Jyväskylä) Convergence rate of random walk approximations of mean field BSDEs
Stefan Geiss (University of Jyväskylä) On the approximation of a class of stochastic integrals with anticipating integrands
Julius Graf (University of California, Berkeley) Learning Market Making with Closing Auctions
Emma Hubert (Université Paris Dauphine & PSL) Revisiting contract theory with volatility control
Idris Kharroubi (Sorbonne University) TBA
Céline Labart (Université Savoie Mont-Blanc) Numerical study for optimal switching problems
Xinyu Li (University of Oxford) An alpha-potential game framework for N-player dynamic games
Cyril Nefzaoui Blanchard (Université Evry-Paris Saclay) Piecewise constant policy approximation for the Quantile Hedging problem
Antonio Ocello (ENSAE Paris, CREST, IP Paris) Convergence Guarantees for Score-Based Generative Models: From Continuous Diffusions to Discrete Data
Nadia Oudjane (EDF R&D) Optimizing and learning over the space of probability measures to manage flexibilities in power systems
Guodong Pang (Rice University Houston) New Relative Value Iteration and Q-Learning Algorithms for Ergodic Risk Sensitive Control of Markov Chains
Huyen Pham (Ecole Polytechnique) Learning generative dynamics with soft law constraints: a McKean-Vlasov FBSDE approach
Justin Ruelland (Université Paris Cité) Option-Surface Fitting as a Dynamical Optimal Transport Problem.
Simon Sananes (Université Paris Cité) Stochastic Policy Gradient Methods in the Uncertain Volatility Model
Enrico Sartor (CNRS, Université Paris-Saclay) A Particle Perspective on Partially Observed Stochastic Control
David Siska (University of Edinburgh) Convergence of actor-critic algorithms for discrete and continuous time RL
Haoze Yan ( UC Berkeley) Controlled Hawkes Jump–Diffusions and CT-DDPG via Markov Approximation
Yanzhao Yang (University of Oxford) Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes
SPONSOR
