paper-with-me

Papers

Exact Formulas for Finite-Time Estimation Errors of Decentralized Temporal Difference Learning with Linear Function Approximation

2022-04-20 · Xingang Guo, Bin Hu

In this paper, we consider the policy evaluation problem in multi-agent reinforcement learning (MARL) and derive exact closed-form formulas for the finite-time mean-squared estimation errors of decentralized temporal difference (TD) learning with linear function approximation. Our analysis hinges upon the fact that the decentralized TD learning method can be viewed as a Markov jump linear system (MJLS). Then standard MJLS theory can be applied to quantify the mean and covariance matrix of the estimation error of the decentralized TD method at every time step. Various implications of our exact formulas on the algorithm performance are also discussed. An interesting finding is that under a necessary and sufficient stability condition, the mean-squared TD estimation error will converge to an exact limit at a specific exponential rate.

📄 PDF Abstract BibTeX arXiv:2204.09801

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Singular ridge regression with homoscedastic residuals: generalization error with estimated parameters

2016-05-29 · Lyudmila Grigoryeva, Juan-Pablo Ortega

This paper characterizes the conditional distribution properties of the finite sample ridge regression estimator and uses that result to evaluate total regression and generalization errors that incorporate the inaccuraci…

parameter estimationregression

Are Hitting Formulas Hard for Resolution?

2022-06-30 · Tomáš Peitl, Stefan Szeider

Hitting formulas, introduced by Iwama, are an unusual class of propositional CNF formulas. Not only is their satisfiability decidable in polynomial time, but even their models can be counted in closed form. This stands i…

New Metric Formulas that Include Measurement Errors in Machine Learning for Natural Sciences

2022-09-30 · Umberto Michelucci, Francesca Venturini

The application of machine learning to physics problems is widely found in the scientific literature. Both regression and classification problems are addressed by a large array of techniques that involve learning algorit…

regression

Reliable Error Estimation for PINNs: Lower and Upper A Posteriori Bounds

2026-06-10 · Ismail Huseynov, Arzu Ahmadova, Agamirza Bashirov arxiv

Physics-informed neural networks (PINNs) combine machine learning with physical laws to solve differential equations. While existing results provide rigorous \emph{a posteriori} upper bounds for PINN prediction errors, c…

Extensive networks would eliminate the demand for pricing formulas

2021-01-22 · Jaegi Jeon, Kyunghyun Park, Jeonggyu Huh

In this study, we generate a large number of implied volatilities for the Stochastic Alpha Beta Rho (SABR) model using a graphics processing unit (GPU) based simulation and enable an extensive neural network to learn the…

GPU