mlsanityData to 14 Oct 2026

Recent Developments in Machine Learning Methods for Stochastic Control and Games

arXiv 2303.10257 ↗First posted 17 Mar 2023math.OC cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Stochastic optimal control and games have a wide range of applications, from finance and economics to social sciences, robotics, and energy management. Many real-world applications involve complex models that have driven the development of sophisticated numerical methods. Recently, computational methods based on machine learning have been developed for solving stochastic control problems and games. In this review, we focus on deep learning methods that have unlocked the possibility of solving such problems, even in high dimensions or when the structure is very complex, beyond what traditional numerical methods can achieve. We consider mostly the continuous time and continuous space setting. Many of the new approaches build on recent neural-network-based methods for solving high-dimensional partial differential equations or backward stochastic differential equations, or on model-free reinforcement learning for Markov decision processes that have led to breakthrough results. This paper provides an introduction to these methods and summarizes the state-of-the-art works at the crossroad of machine learning and stochastic control and games.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 54 of its 312 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

54 of 312 references.

References · 54

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  3. 2013Generating Sequences With Recurrent Neural Networkscited by 554
  4. 2017Deep Reinforcement Learning: An Overviewcited by 333
  5. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
  6. 2018Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulatorcited by 250
  7. 2020Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularizationcited by 176
  8. 2017Approximating Continuous Functions by ReLU Nets of Minimal Widthcited by 122
  9. 2021Recent Advances in Reinforcement Learning in Financecited by 110
  10. 2021Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithmscited by 101
  11. 2020Game-Theoretic Multiagent Reinforcement Learningcited by 94
  12. 2019Deep Signature Transformscited by 75
38 more
  1. 2021Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learningcited by 73
  2. 2022Generic bounds on the approximation error for physics-informed (and) operator learningcited by 65
  3. 2022Error estimates for physics informed neural networks approximating the Navier-Stokes equationscited by 63
  4. 2022Learning in Mean Field Games: A Surveycited by 61
  5. 2019Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learningcited by 59
  6. 2016Deep Learning Approximation for Stochastic Control Problemscited by 55
  7. 2020Unified Reinforcement Q-Learning for Mean Field Game and Control Problemscited by 49
  8. 2020Q-Learning in Regularized Mean-field Gamescited by 42
  9. 2022Scalable Deep Reinforcement Learning Algorithms for Mean Field Gamescited by 38
  10. 2020Alternating the Population and Control Neural Networks to Solve High-Dimensional Stochastic Mean-Field Gamescited by 35
  11. 2019Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: II -- The Finite Horizon Casecited by 34
  12. 2019Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methodscited by 28
  13. 2021Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approachcited by 28
  14. 2021Generalization in Mean Field Games by Learning Master Policiescited by 28
  15. 2021Neural networks-based algorithms for stochastic control and PDEs in financecited by 26
  16. 2021On the Universality of Graph Neural Networks on Large Random Graphscited by 26
  17. 2019Mean-field Markov decision processes with common noise and open-loop controlscited by 25
  18. 2019Dynamic Programming Principles for Mean-Field Controls with Learningcited by 23
  19. 2021Deep Learning for Mean Field Games and Mean Field Control with Applications to Financecited by 20
  20. 2019Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Gamescited by 16
  21. 2019Deep Q-Learning for Nash Equilibria: Nash-DQNcited by 14
  22. 2021Signatured Deep Fictitious Play for Mean Field Games with Common Noisecited by 12
  23. 2021DeepHAM: A Global Solution Method for Heterogeneous Agent Models with Aggregate Shockscited by 11
  24. 2020Learning a functional control for high-frequency financecited by 10
  25. 2020Convergence of Deep Fictitious Play for Stochastic Differential Gamescited by 10
  26. 2021A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problemscited by 10
  27. 2022Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problemscited by 9
  28. 2020Connecting GANs, MFGs, and OTcited by 8
  29. 2019Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: I -- The Ergodic Casecited by 6
  30. 2020Optimal Policies for a Pandemic: A Stochastic Game Approach and a Deep Learning Algorithmcited by 6
  31. 2022Deep Signature Algorithm for Multi-dimensional Path-Dependent Optionscited by 6
  32. 2020Large-Scale Multi-Agent Deep FBSDEscited by 5
  33. 2022Temporal Difference Learning with Continuous Time and State in the Stochastic Settingcited by 5
  34. 2014A Probabilistic approach to classical solutions of the master equation for large population equilibriacited by 4
  35. 2020A posteriori error estimates for fully coupled McKean-Vlasov forward-backward SDEscited by 4
  36. 2020Deep Learning for Constrained Utility Maximisationcited by 4
  37. 2022A Machine Learning Enhanced Algorithm for the Optimal Landing Problemcited by 4
  38. 2021Exploration noise for learning linear-quadratic mean field gamescited by 3

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 12; 2026: 7.

24 papers.

Sort:

By area:

  1. 2024Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problemscited by 7
  2. 2024Deep Backward and Galerkin Methods for the Finite State Master Equationcited by 6
  3. 2024An Overview on Machine Learning Methods for Partial Differential Equations: from Physics Informed Neural Networks to Deep Operator Learningcited by 6
  4. 2025Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networkscited by 6
  5. 2025One model to solve them all: 2BSDE families via neural operatorscited by 4
  6. 2024An Efficient On-Policy Deep Learning Framework for Stochastic Optimal Controlcited by 3
  7. 2025Reconciling Discrete-Time Mixed Policies and Continuous-Time Relaxed Controls in Reinforcement Learning and Stochastic Controlcited by 3
  8. 2025Neural Actor-Critic Methods for Hamilton-Jacobi-Bellman PDEs: Asymptotic Analysis and Numerical Studiescited by 3
  9. 2025Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamicscited by 2
  10. 2026Deep Hilbert--Galerkin Methods for Infinite-Dimensional PDEs and Optimal Controlcited by 2
  11. 2025PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learningcited by 1
  12. 2025Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architecturescited by 1
12 more
  1. 2024Why does the two-timescale Q-learning converge to different mean field solutions? A unified convergence analysiscited by 0
  2. 2025Consensus Based Stochastic Controlcited by 0
  3. 2025An Optimization-Based Framework for Solving Forward-Backward Stochastic Differential Equations: Convergence Analysis and Error Boundscited by 0
  4. 2025Mean-Field Generalisation Bounds for Learning Controls in Stochastic Environmentscited by 0
  5. 2025Error analysis for the deep Kolmogorov methodcited by 0
  6. 2025DeepPAAC: A New Deep Galerkin Method for Principal-Agent Problemscited by 0
  7. 2026Recurrent Structural Policy Gradient for Partially Observable Mean Field Gamescited by 0
  8. 2026Dual Approaches to Stochastic Control via SPDEs and the Pathwise Hopf Formulacited by 0
  9. 2026Robust Q-learning for mean-field control under Wasserstein uncertainty in common noisecited by 0
  10. 2026Path Integral Value Matching for Linear Quadratic Stochastic Optimal Controlcited by 0
  11. 2026Self-supervised In-context Operator Learning for Stochastic Mean-Field Controlcited by 0
  12. 2026Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergencecited by 0