Offline MARL

MARL: Multi-Agent Reinforcement Learning

Overview

Offline MARL studies how multiple agents can learn to cooperate or compete from logged trajectories, where their actions affect one another and new mistakes cannot be tested freely. Approaches include behavior cloning, conservative value learning, sequence models, diffusion and flow policies, and world models; theoretical work also studies equilibrium guarantees under dataset coverage assumptions. Methods are evaluated in settings such as SMAC and MPE coordination tasks, continuous-control benchmarks, traffic management, and wireless resource allocation, often with decentralized execution. A central challenge is that policies can take joint actions unlike those in the data, making value estimates unreliable and coordination brittle; current work explores support-aware learning, test-time planning, and stronger generalization while balancing performance, safety, and reliable guarantees.

Latest papers

CardsList

32 papers2 papers in the last four weeks, down 60% on the four weeks before. 0.0% of all new papers.

  1. A Recipe for Stable Offline Multi-agent Reinforcement Learning

    Mar 9, 2026Dongsu Lee, Daehee Lee, Amy ZhangOffline MARLActor-Critic Methods

  2. Matching Multiple Experts: On the Exploitability of Multi-Agent Imitation Learning

    Feb 24, 2026Antoine Bergerault, Volkan Cevher, Negar MehrImitation LearningOffline MARL