REVIEW 1 cited by
Mirror Descent for Stochastic Control Problems with Measure-valued Controls
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
This paper studies the convergence of the mirror descent algorithm for finite horizon stochastic control problems with measure-valued control processes. The control objective involves a convex regularisation function, denoted as $h$, with regularisation strength determined by the weight $\tau\ge 0$. The setting covers regularised relaxed control problems. Under suitable conditions, we establish the relative smoothness and convexity of the control objective with respect to the Bregman divergence of $h$, and prove linear convergence of the algorithm for $\tau=0$ and exponential convergence for $\tau>0$. The results apply to common regularisers including relative entropy, $\chi^2$-divergence, and entropic Wasserstein costs. This validates recent reinforcement learning heuristics that adding regularisation accelerates the convergence of gradient methods. The proof exploits careful regularity estimates of backward stochastic differential equations in the bounded mean oscillation norm.
Forward citations
Cited by 1 Pith paper
-
Mirror descent for constrained stochastic control problems
Under uniform convexity of the Hamiltonian, continuous-time mirror descent converges linearly; under strong convexity relative to a Bregman divergence, it converges exponentially.
Discussion (0). Continue with ORCID to comment.