Research map / Multi-agent systems and games / Cooperative multi-agent RL
Submodular Multi-Agent Reinforcement Learning for Effective Online Distributed Task Allocation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies multi-agent RL with submodular team utilities for online distributed task allocation, using a continuous relaxation over partition-matroid feasible joint actions.
Problem
Distributed online task allocation where N agents choose actions from local categorical distributions and team utility is a non-additive submodular set function; the abstract indicates the standard continuous relaxation of set utility is the starting point for the difficulty.
Approach
Models feasible joint actions as a partition matroid over agent-action pairs and builds an MARL approach around submodular utilities; the abstract is truncated so the specific mechanism beyond the relaxation is not stated.
Closest papers by meaning
- Multi-Agent Reinforcement Learning with Submodular Reward (ICML 2026 · similarity 0.92)
- Submodular Reinforcement Learning (ICLR 2024 · similarity 0.89)
- Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency (ICLR 2025 · similarity 0.88)
- Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives (NeurIPS 2025 · similarity 0.88)
- Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems (NeurIPS 2026 · similarity 0.88)
- AgentMixer: Multi-Agent Correlated Policy Factorization (AAAI 2025 · similarity 0.88)
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.