A primal-dual reformulation of the stochastic LQR with multiplicative noise yields a partially model-free policy iteration algorithm, with convergence guaranteed for the model-based case.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning-based primal-dual optimal control of discrete-time stochastic systems with multiplicative noise
A primal-dual reformulation of the stochastic LQR with multiplicative noise yields a partially model-free policy iteration algorithm, with convergence guaranteed for the model-based case.