A conditional universal approximation theorem shows that residual operator-block DQNs with depth aligned to Bellman iterations can approximate the optimal Q-function, assuming a neural operator class with controlled Lipschitz outputs exists.
Tensor spaces and numerical tensor calculus, volume 42
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Universal Approximation Theorem for Deep Q-Learning via FBSDE System
A conditional universal approximation theorem shows that residual operator-block DQNs with depth aligned to Bellman iterations can approximate the optimal Q-function, assuming a neural operator class with controlled Lipschitz outputs exists.