A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise
M. Forzo, E. Monzio Compagnoni, A. Russo, A. Pacchiano
stat.ML, cs.LG, math.PR
Submitted: 2026-06-16
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Robust $\widetilde{\mathcal{O}}(1/\sqrt{T})$ Rate for Unprojected TD Learning with Linear Function Approximation
- A Simple Finite-Time Analysis of TD Learning with Linear Function Approximation
- Statistical inference for Linear Stochastic Approximation with Markovian Noise
- Rates of Convergence in the Central Limit Theorem for Markov Chains, with an Application to TD Learning
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches