Deep reinforcement learning for weakly coupled MDP's with continuous actions - Architecture, Systèmes, Réseaux
Conference Papers Year : 2024

Deep reinforcement learning for weakly coupled MDP's with continuous actions

Abstract

This paper introduces the Lagrange Policy for Continuous Actions (LPCA), a reinforcement learning algorithm specifically designed for weakly coupled MDP problems with continuous action spaces. LPCA addresses the chal- lenge of resource constraints dependent on continuous actions by introducing a Lagrange relaxation of the weakly coupled MDP problem within a neural network framework for Q-value computation. This approach effectively decouples the MDP, enabling efficient policy learning in resource-constrained environments. We present two variations of LPCA: LPCA-DE, which utilizes differential evolu- tion for global optimization, and LPCA-Greedy, a method that incrementally and greadily selects actions based on Q-value gradients. Comparative analysis against other state-of-the-art techniques across various settings highlight LPCA’s robust- ness and efficiency in managing resource allocation while maximizing rewards.
Fichier principal
Vignette du fichier
Deep reinforcement learning for weakly coupled MDPs with continuous actions.pdf (388.65 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04594762 , version 1 (30-05-2024)
hal-04594762 , version 2 (11-06-2024)

Identifiers

Cite

Francisco Robledo, Urtzi Ayesta, Konstantin Avrachenkov. Deep reinforcement learning for weakly coupled MDP's with continuous actions. ACM SIGMETRICS / ASMTA 2024, Jun 2024, Venise, Italy. ⟨hal-04594762v2⟩
462 View
61 Download

Altmetric

Share

More