Search Results for author:
Found 26 papers, 4 papers with code
Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspective
This MFTG NE is then shown to be $\mathcal{O}(1/M)$-NE for the finite population game where $M$ is a lower bound on the number of agents in each team.
Deep Backward and Galerkin Methods for the Finite State Master Equation
This paper proposes and analyzes two neural network methods to solve the master equation for finite-state mean field games (MFGs).
A Deep Learning Method for Optimal Investment Under Relative Performance Criteria Among Heterogeneous Agents
By passing to the limit, a game with a continuum of players is obtained, in which the interactions are through a graphon.
Learning Discrete-Time Major-Minor Mean Field Games
We propose a novel discrete time version of major-minor MFGs (M3FGs), along with a learning algorithm based on fictitious play and partitioning the probability simplex.
Recent Developments in Machine Learning Methods for Stochastic Control and Games
Recently, computational methods based on machine learning have been developed for solving stochastic control problems and games.
Actor-Critic learning for mean-field control in continuous time
We study policy gradient for mean-field control in continuous time in a reinforcement learning setting.
Deep Learning for Mean Field Optimal Transport
The first one is based on directly learning an optimal control.
Learning in Mean Field Games: A Survey
Non-cooperative and cooperative games with a very large number of players have many applications but remain generally intractable when the number of players increases.
Scalable Deep Reinforcement Learning Algorithms for Mean Field Games
One limiting factor to further scale up using RL is that existing algorithms to solve MFGs require the mixing of approximated quantities such as strategies or $q$-values.
Generalization in Mean Field Games by Learning Master Policies
Mean Field Games (MFGs) can potentially scale multi-agent systems to extremely large populations of agents.
Performance of a Markovian neural network versus dynamic programming on a fishing control problem
Fishing quotas are unpleasant but efficient to control the productivity of a fishing site.
Deep Learning for Mean Field Games and Mean Field Control with Applications to Finance
Financial markets and more generally macro-economic models involve a large number of individuals interacting through variables such as prices resulting from the aggregate behavior of all the agents.
Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint
Mean-field Games (MFGs) are a continuous approximation of many-agent RL.
Mean Field Games Flock! The Reinforcement Learning Way
We present a method enabling a large number of agents to learn how to flock, which is a natural behavior observed in large populations of animals.
Scaling up Mean Field Games with Online Mirror Descent
We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD).
Policy Optimization for Linear-Quadratic Zero-Sum Mean-Field Type Games
In particular, the case in which the transition and utility functions depend on the state, the action of the controllers, and the mean of the state and the actions, is investigated.
Linear-Quadratic Zero-Sum Mean-Field Type Games: Optimality Conditions and Policy Optimization
In particular, the case in which the transition and utility functions depend on the state, the action of the controllers, and the mean of the state and the actions, is investigated.
Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications
In this paper, we deepen the analysis of continuous time Fictitious Play learning algorithm to the consideration of various finite state Mean Field Game settings (finite horizon, $\gamma$-discounted), allowing in particular for the introduction of an additional common noise.
Unified Reinforcement Q-Learning for Mean Field Game and Control Problems
We present a Reinforcement Learning (RL) algorithm to solve infinite horizon asymptotic Mean Field Game (MFG) and Mean Field Control (MFC) problems.
Learning a functional control for high-frequency finance
The issue of scarcity of financial data is solved by transfer learning: the neural network is first trained on trajectories generated thanks to a Monte-Carlo scheme, leading to a good initialization before training on historical trajectories.
Connecting GANs, MFGs, and OT
Generative adversarial networks (GANs) have enjoyed tremendous success in image generation and processing, and have recently attracted growing interests in financial modelings.
Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning
We study infinite horizon discounted Mean Field Control (MFC) problems with common noise through the lens of Mean Field Markov Decision Processes (MFMDP).
Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods
We investigate reinforcement learning for mean field control problems in discrete time, which can be viewed as Markov decision processes for a large number of exchangeable agents interacting in a mean field manner.
Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: II -- The Finite Horizon Case
The second method tackles a generic forward-backward stochastic differential equation system (FBSDE) of McKean-Vlasov type, and relies on suitable reformulation as a mean field control problem.
Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: I -- The Ergodic Case
Finally, we illustrate the fact that, although the first algorithm is specifically designed for mean field control problems, the second one is more general and can also be applied to the partial differential equation systems arising in the theory of mean field games.
On the Convergence of Model Free Learning in Mean Field Games
In order to design scalable algorithms for systems with a large population of interacting agents (e. g. swarms), this paper focuses on Mean Field MAS, where the number of agents is asymptotically infinite.
