REVIEW 4 cited by
A Primal-Dual Approach to Constrained Markov Decision Processes
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
A Primal-Dual Approach to Constrained Markov Decision Processes
abstract
In many operations management problems, we need to make decisions sequentially to minimize the cost while satisfying certain constraints. One modeling approach to study such problems is constrained Markov decision process (CMDP). When solving the CMDP to derive good operational policies, there are two key challenges: one is the prohibitively large state space and action space; the other is the hard-to-compute transition kernel. In this work, we develop a sampling-based primal-dual algorithm to solve CMDPs. Our approach alternatively applies regularized policy iteration to improve the policy and subgradient ascent to maintain the constraints. Under mild regularity conditions, we show that the algorithm converges at rate $ O(\log(T)/\sqrt{T})$, where T is the number of iterations. When the CMDP has a weakly coupled structure, our approach can substantially reduce the dimension of the problem through an embedded decomposition. We apply the algorithm to two important applications with weakly coupled structures: multi-product inventory management and multi-class queue scheduling, and show that it generates controls that outperform state-of-art heuristics.
Forward citations
Cited by 4 Pith papers
-
Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
HPO enables unbiased policy optimization in hybrid action spaces by mixing differentiable simulation gradients with score-function estimates, outperforming PPO as continuous dimensions increase.
-
Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses
A new primal-dual algorithm for adversarial linear CMDPs achieves the first sublinear regret and constraint violation bounds of order K to the 3/4 using weighted LogSumExp softmax policies with periodic mixing and reg...
-
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
Presents the first algorithm to identify an ε-optimal policy in robust constrained MDPs via epigraph form and bisection search with Õ(ε^{-4}) robust policy evaluations.
-
Inpatient Overflow Management with Proximal Policy Optimization
A PPO reinforcement learning method using atomic actions, partially-shared policies, and queueing-informed value approximation scales inpatient overflow optimization to hospital systems with 20 patient classes and war...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.