Saved in:
Bibliographic Details
Main Authors: Khan, Nouman, Subramanian, Vijay G.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.12635
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913133090570240
author Khan, Nouman
Subramanian, Vijay G.
author_facet Khan, Nouman
Subramanian, Vijay G.
contents Constrained decentralized team problem formulations are good models for many cooperative multi-agent systems. Constraints necessitate randomization when solving for optimal solutions -- past results show that joint randomization in the team is in general necessary for (strong) Lagrangian duality to hold -- , but a better understanding of randomization still remains. For a partially observed multi-agent system with a Borel hidden state, countable observations, and finite actions, we prove the following: \textit{i}) independently randomized decentralized policy-profiles -- whether behavioral or pure -- induce the same occupation measures (on joint-history and joint-action pairs) as decentralized behavioral policy-profiles; and \textit{ii}) jointly randomized behavioral and pure decentralized policy-profiles induce the same occupation measures. Restricting to finite observations, we also prove that joint mixtures of decentralized policy-profiles (both pure and behavioral) and common information based behavioral coordination policies (also mixtures of them) induce the same occupation measures. This generalizes past work that shows equivalence between pure decentralized policy-profiles and pure coordination policies. These results can be used to develop further results on Lagrangian duality, the minimum number of randomizations needed in an optimal behavioral coordination policy, and learning based schemes that can find approximately optimal solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12635
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On Equivalence Between Decentralized Policy-Profile Mixtures and Behavioral Coordination Policies in Multi-Agent Systems
Khan, Nouman
Subramanian, Vijay G.
Optimization and Control
Constrained decentralized team problem formulations are good models for many cooperative multi-agent systems. Constraints necessitate randomization when solving for optimal solutions -- past results show that joint randomization in the team is in general necessary for (strong) Lagrangian duality to hold -- , but a better understanding of randomization still remains. For a partially observed multi-agent system with a Borel hidden state, countable observations, and finite actions, we prove the following: \textit{i}) independently randomized decentralized policy-profiles -- whether behavioral or pure -- induce the same occupation measures (on joint-history and joint-action pairs) as decentralized behavioral policy-profiles; and \textit{ii}) jointly randomized behavioral and pure decentralized policy-profiles induce the same occupation measures. Restricting to finite observations, we also prove that joint mixtures of decentralized policy-profiles (both pure and behavioral) and common information based behavioral coordination policies (also mixtures of them) induce the same occupation measures. This generalizes past work that shows equivalence between pure decentralized policy-profiles and pure coordination policies. These results can be used to develop further results on Lagrangian duality, the minimum number of randomizations needed in an optimal behavioral coordination policy, and learning based schemes that can find approximately optimal solutions.
title On Equivalence Between Decentralized Policy-Profile Mixtures and Behavioral Coordination Policies in Multi-Agent Systems
topic Optimization and Control
url https://arxiv.org/abs/2504.12635