Temporal-difference learning with nonlinear function approximation: lazy training and mean field regimes release_njce63afnzfgvmhzj2c275nrxu

by Andrea Agazzi, Jianfeng Lu

Released as a article .

2020  

Abstract

We discuss the approximation of the value function for infinite-horizon discounted Markov Reward Processes (MRP) with nonlinear functions trained with the Temporal-Difference (TD) learning algorithm. We first consider this problem under a certain scaling of the approximating function, leading to a regime called lazy training. In this regime, the parameters of the model vary only slightly during the learning process, a feature that has recently been observed in the training of neural networks, where the scaling we study arises naturally, implicit in the initialization of their parameters. Both in the under- and over-parametrized frameworks, we prove exponential convergence to local, respectively global minimizers of the above algorithm in the lazy training regime. We then compare this scaling of the parameters to the mean-field regime, where the approximately linear behavior of the model is lost. Under this alternative scaling we prove that all fixed points of the dynamics in parameter space are global minimizers. We finally give examples of our convergence results in the case of models that diverge if trained with non-lazy TD learning, and in the case of neural networks.
In text/plain format

Archived Files and Locations

application/pdf  879.7 kB
file_oqgytefdrzgqbdensrx4fu3hlu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-06-30
Version   v4
Language   en ?
arXiv  1905.10917v4
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: b1697c52-b1ea-425a-ba33-1c412b69459c
API URL: JSON