A DQN built from residual blocks inherits universal approximation for continuous Q-functions, but the claimed convergence proof assumes the Lyapunov condition and exact representability that essentially assert the result.
Without loss of generality, we can assume that V∗(t0,s 0) = ϕ(t0,s 0)
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 of Deep Q-Networks
A DQN built from residual blocks inherits universal approximation for continuous Q-functions, but the claimed convergence proof assumes the Lyapunov condition and exact representability that essentially assert the result.