Foundational geometric, stationarity, and convergence results are derived for Bellman residual minimization applied to policy optimization in MDPs.
The following result establishes the convergence of the algorithm under the above assumptions
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
-
Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence
Foundational geometric, stationarity, and convergence results are derived for Bellman residual minimization applied to policy optimization in MDPs.