Signatured Deep Fictitious Play for Mean Field Games with Common Noise
- URL: http://arxiv.org/abs/2106.03272v1
- Date: Sun, 6 Jun 2021 23:09:46 GMT
- Title: Signatured Deep Fictitious Play for Mean Field Games with Common Noise
- Authors: Ming Min, Ruimeng Hu
- Abstract summary: Existing deep learning methods for solving mean-field games (MFGs) with common noise fix the sampling common noise paths and then solve the corresponding MFGs.
We propose a novel single-loop algorithm, named signatured deep fictitious play, by which we can work with the unfixed common noise setup to avoid the nested-loop structure.
The proposed algorithm can accurately capture the effect of common uncertainty changes on mean-field equilibria without further training of neural networks.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing deep learning methods for solving mean-field games (MFGs) with
common noise fix the sampling common noise paths and then solve the
corresponding MFGs. This leads to a nested-loop structure with millions of
simulations of common noise paths in order to produce accurate solutions, which
results in prohibitive computational cost and limits the applications to a
large extent. In this paper, based on the rough path theory, we propose a novel
single-loop algorithm, named signatured deep fictitious play, by which we can
work with the unfixed common noise setup to avoid the nested-loop structure and
reduce the computational complexity significantly. The proposed algorithm can
accurately capture the effect of common uncertainty changes on mean-field
equilibria without further training of neural networks, as previously needed in
the existing machine learning algorithms. The efficiency is supported by three
applications, including linear-quadratic MFGs, mean-field portfolio game, and
mean-field game of optimal consumption and investment. Overall, we provide a
new point of view from the rough path theory to solve MFGs with common noise
with significantly improved efficiency and an extensive range of applications.
In addition, we report the first deep learning work to deal with extended MFGs
(a mean-field interaction via both the states and controls) with common noise.
Related papers
- Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning [50.92957910121088]
This work designs and analyzes a novel set of algorithms for multi-agent reinforcement learning (MARL) based on the principle of information-directed sampling (IDS)
For episodic two-player zero-sum MGs, we present three sample-efficient algorithms for learning Nash equilibrium.
We extend Reg-MAIDS to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample efficient manner.
arXiv Detail & Related papers (2024-04-30T06:48:56Z) - Optimized Noise Suppression for Quantum Circuits [0.40964539027092917]
Crosstalk noise is a severe error source in, e.g., cross-resonance based superconducting quantum processors.
Intrepid programming algorithm extends previous work on optimized qubit routing by swap insertion.
We evaluate the proposed method by characterizing crosstalk noise for two chips with up to 127 qubits.
arXiv Detail & Related papers (2024-01-12T07:34:59Z) - Learning Discrete-Time Major-Minor Mean Field Games [61.09249862334384]
We propose a novel discrete time version of major-minor MFGs (M3FGs) and a learning algorithm based on fictitious play and partitioning the probability simplex.
M3FGs generalize MFGs with common noise and can handle not only random exogeneous environment states but also major players.
arXiv Detail & Related papers (2023-12-17T18:22:08Z) - Layering and subpool exploration for adaptive Variational Quantum
Eigensolvers: Reducing circuit depth, runtime, and susceptibility to noise [0.0]
Adaptive variational quantum eigensolvers (ADAPT-VQEs) are promising candidates for simulations of strongly correlated systems.
Recent efforts have been directed towards compactifying, or layering, their ansatz circuits.
We show that layering leads to an improved noise resilience with respect to amplitude-damping and dephasing noise.
arXiv Detail & Related papers (2023-08-22T18:00:02Z) - Distributed Extra-gradient with Optimal Complexity and Communication
Guarantees [60.571030754252824]
We consider monotone variational inequality (VI) problems in multi-GPU settings where multiple processors/workers/clients have access to local dual vectors.
Extra-gradient, which is a de facto algorithm for monotone VI problems, has not been designed to be communication-efficient.
We propose a quantized generalized extra-gradient (Q-GenX), which is an unbiased and adaptive compression method tailored to solve VIs.
arXiv Detail & Related papers (2023-08-17T21:15:04Z) - Learning in Congestion Games with Bandit Feedback [45.4542525044623]
We investigate congestion games, a class of games with benign theoretical structure and broad real-world applications.
We first propose a centralized algorithm based on the optimism in the face of uncertainty principle for congestion games.
We then propose a decentralized algorithm via a novel combination of the Frank-Wolfe method and G-optimal design.
arXiv Detail & Related papers (2022-06-04T02:32:26Z) - Accelerating Noisy VQE Optimization with Gaussian Processes [0.0]
We introduce the use of Gaussian Processes (GP) as surrogate models to reduce the impact of noise.
ImFil is a state-of-the-art, gradient-free method, which in comparative studies has been shown to outperform on noisy VQE problems.
We show that when noise is present, the GP+ImFil approach finds results closer to the true global minimum in fewer evaluations than standalone ImFil.
arXiv Detail & Related papers (2022-04-15T05:01:14Z) - Multiview point cloud registration with anisotropic and space-varying
localization noise [1.5499426028105903]
We address the problem of registering multiple point clouds corrupted with high anisotropic localization noise.
Existing methods are based on an implicit assumption of space-invariant isotropic noise.
We show that our noise handling strategy improves significantly the robustness to high levels of anisotropic noise.
arXiv Detail & Related papers (2022-01-03T15:21:24Z) - Learning based signal detection for MIMO systems with unknown noise
statistics [84.02122699723536]
This paper aims to devise a generalized maximum likelihood (ML) estimator to robustly detect signals with unknown noise statistics.
In practice, there is little or even no statistical knowledge on the system noise, which in many cases is non-Gaussian, impulsive and not analyzable.
Our framework is driven by an unsupervised learning approach, where only the noise samples are required.
arXiv Detail & Related papers (2021-01-21T04:48:15Z) - Plug-And-Play Learned Gaussian-mixture Approximate Message Passing [71.74028918819046]
We propose a plug-and-play compressed sensing (CS) recovery algorithm suitable for any i.i.d. source prior.
Our algorithm builds upon Borgerding's learned AMP (LAMP), yet significantly improves it by adopting a universal denoising function within the algorithm.
Numerical evaluation shows that the L-GM-AMP algorithm achieves state-of-the-art performance without any knowledge of the source prior.
arXiv Detail & Related papers (2020-11-18T16:40:45Z) - Non-Local Spatial Propagation Network for Depth Completion [82.60915972250706]
We propose a robust and efficient end-to-end non-local spatial propagation network for depth completion.
The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pixel.
We show that the proposed algorithm is superior to conventional algorithms in terms of depth completion accuracy and robustness to the mixed-depth problem.
arXiv Detail & Related papers (2020-07-20T12:26:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.