AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

A Separation Principle for Cooperative Multi-Agent Reinforcement Learning

Lucia Pezzetti, Nicolas Lanzetti, Antonio Terpin, Florian Dorfler, Giorgia Ramponi

NeurIPS 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies cooperative MARL with decoupled noisy agent dynamics coupled through a population objective, motivated by fleet mobility, and proposes a separation principle for learning in this setting.

Problem

Cooperative multi-agent RL where agents evolve under decoupled noisy dynamics but are coupled via a population-level objective (e.g., a mobility operator managing a vehicle fleet to meet customer demand); existing MARL algorithms are said to not exploit this structure.

Approach

Exploits the decoupled-dynamics-plus-population-objective structure via a separation principle, as stated in the title; the abstract is truncated so the specific mechanism is not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
separate assignment (optimal transport) from single-agent routing instead of learning a joint MARL policySALT · Stochastic grid world (N=7)average travel time: 23-61% reduction vs MARL baselinesImproved
swap the single-agent learner among Q-learning, DDQN, PPO and A2C (ablation)SALT · Stochastic grid world (N=7)average travel timeNo clear effect
use target-conditioned single-agent PPO in SALT instead of MAPPO as population size growsSALT-PPO · Grid world scaling, N=2 to 128environment interactions to reach-rate milestones: up to 480x fewer interactionsImproved
scale population to N=8 and beyond with MAPPO versus SALT-PPOMAPPO · Grid world scaling, 2e9 interaction budgetreach-rate milestone: MAPPO fails 70% milestone at N=8; SALT-PPO reaches 99% up to N=128Hurt
learned target-conditioned Q policy with optimal transport assignment versus static shortest-path routingSALT-Q · Southern Manhattan road networktravel time improvement: 14.8% (N=1) to 21.3% (N=100)Improved
evaluate policy trained with 20 vehicles on unseen fleet sizes without retrainingSALT-Q · Southern Manhattan road network, fleets of 1-100travel time improvementNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy