Q-functions of infinite-horizon discounted MDPs with finite action sets are approximable by leaky ReLU networks with polynomially growing parameter counts, provided rewards and transitions are themselves DNN-approximable.
Deep ReLU neural networks overcome the curse of dimensionality when approximating semilinear partial integro-differential equations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this paper we consider PIDEs with gradient-independent Lipschitz continuous nonlinearities and prove that deep neural networks with ReLU activation function can approximate solutions of such semilinear PIDEs without curse of dimensionality in the sense that the required number of parameters in the deep neural networks increases at most polynomially in both the dimension $ d $ of the corresponding PIDE and the reciprocal of the prescribed accuracy $\epsilon $.
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
ACCEPT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Deep neural networks can provably solve Bellman equations for Markov decision processes without the curse of dimensionality
Q-functions of infinite-horizon discounted MDPs with finite action sets are approximable by leaky ReLU networks with polynomially growing parameter counts, provided rewards and transitions are themselves DNN-approximable.