English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we study the dynamics of temporal difference learning withneural network-based value function approximation over a general state space,namely, \emph{Neural TD learning}. We consider two practically used algorithms,projection-free and max-norm regularized Neural TD learning, and establish thefirst convergence bounds for these algorithms. An interesting observation fromour results is that max-norm regularization can dramatically improve theperformance of TD learning algorithms, both in terms of sample complexity andoverparameterization. In particular, we prove that max-norm regularizationimproves state-of-the-art sample complexity and overparameterization bounds.The results in this work rely on a novel Lyapunov drift analysis of the networkparameters as a stopped and controlled random process.

Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation