Q-learning with linear function approximation is recast as a switched linear system whose mean dynamics converge precisely when the joint spectral radius of the switching matrices is less than one.
Dynamic programming and optimal con trol 4th edition, volume ii
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Switching System Theory of Q-Learning with Linear Function Approximation
Q-learning with linear function approximation is recast as a switched linear system whose mean dynamics converge precisely when the joint spectral radius of the switching matrices is less than one.