Robust Q-learning for mean-field control under Wasserstein uncertainty in common noise

arXiv:2606.20356 · math.OC, cs.AI, cs.LG, math.PR, stat.ML · Submitted 2026-06-18 · Read on arXiv

Mathieu Laurière, Ariel Neufeld, Kyunghyun Park

math.OC, cs.AI, cs.LG, math.PR, stat.ML

Submitted: 2026-06-18

Code: https://github.com/mlauriere/RobustMeanFieldControlQLearning

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Q-learning — 97× in this paper · explained in 3 episodes
• Robustness — 30× in this paper · explained in 6 episodes
• Reinforcement Learning — 21× in this paper · explained in 4 episodes
• Fixed Point — 11× in this paper · explained in 2 episodes
• Quantization — 10× in this paper · explained in 15 episodes
• Planner — 7× in this paper · explained in 3 episodes
• Reward Function — 5× in this paper · explained in 4 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 3× in this paper · explained in 3 episodes
• Sample Complexity — 3× in this paper · explained in 20 episodes
• Wasserstein Distance — 3× in this paper · explained in 6 episodes
• Markov Decision Process (MDP) — 2× in this paper · explained in 16 episodes
• Optimal Transport — 2× in this paper · explained in 5 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Entropy Regularization — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Learning Paradigms — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Variance Reduction — 1× in this paper · explained in 2 episodes

Sources

• Recent Developments in Machine Learning Methods for Stochastic Control and Games
• Markov-Nash equilibria in mean-field games under model uncertainty
• Robust mean-field control under common noise uncertainty
• Learning in Mean Field Games: A Survey
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Mean-Field Games Under Model Uncertainty
• Distributionally Robust Deep Q-Learning
• Continuous-time q-learning for mean-field control with common noise, part-I: Theoretical foundations
• Continuous-time q-learning for mean-field control with common noise, part-II: q-learning algorithms
• Unified continuous-time q-learning for mean-field game and mean-field control problems

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Beyond Aggregate Drift: Optimal Client-Specific Windows in Federated Learning
• Lower Bounds for Randomized Linear-Oracle Optimization over Strongly Convex Sets
• Second-Order Optimization with Asynchronous Curvature