Q-learning error is recast as a switched linear recursion whose exponential rate is exactly the joint spectral radius of a direct switching family, yielding finite-time bounds via a product-defined Lyapunov function.
Taking total expectation and setting ak :=E[V ∞ ε (ek)] gives the scalar recursion ak+1 ≤β 2 ε ak +α 2C2 ε Wmax + (4(1 +γ)B Q)2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lyapunov-Certified Direct Switching Theory for Q-Learning
Q-learning error is recast as a switched linear recursion whose exponential rate is exactly the joint spectral radius of a direct switching family, yielding finite-time bounds via a product-defined Lyapunov function.