Academic Journal

Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction.
Συγγραφείς: YING, DONGHAO1 donghaoy@berkeley.edu, GUO, MENGZI AMY1 mengzi_guo@berkeley.edu, LEE, HYUNIN1 hyunin@berkeley.edu, DING, YUHAO2 yuhao.ding3@gmail.com, LAVAEI, JAVAD1 lavaei@berkeley.edu, SHEN, ZUO-JUN MAX3 maxshen@hku.hk
Πηγή: Journal of Artificial Intelligence Research. 2025, Vol. 83, p1-53. 53p.
Θεματικοί όροι: Markov processes, Algorithms
Περίληψη: We study Concave Constrained Markov Decision Processes (Concave CMDPs) where both the objective and constraints are defined as concave functions of the state-action occupancy measure. We propose the Variance-Reduced Primal-Dual Policy Gradient Algorithm (VR-PDPG), which updates the primal variable via policy gradient ascent and the dual variable via projected sub-gradient descent. Despite the challenges posed by the loss of additivity structure and the nonconcave nature of the problem, we establish the global convergence of VR-PDPG by exploiting a form of hidden concavity. In the exact setting, we prove an O(T-1/3) convergence rate for both the average optimality gap and constraint violation, which further improves to O(T-1/2) under strong concavity of the objective in the occupancy measure. In the sample-based setting, we demonstrate that VR-PDPG achieves an Õ(ε-4) sample complexity for ε-global optimality. Moreover, by incorporating a diminishing pessimistic term into the constraint, we show that VR-PDPG can attain a zero constraint violation without compromising the convergence rate of the optimality gap. Finally, we validate our methods through numerical experiments. [ABSTRACT FROM AUTHOR]
Βάση Δεδομένων: Supplemental Index
Περιγραφή
ISSN:10769757
DOI:10.1613/jair.1.18129