Research map / Multi-agent systems and games / Cooperative multi-agent RL
Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution
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.
Proposes Greedy Sequential Execution (GSE) for cooperative MARL that handles both homogeneous and heterogeneous tasks by sequentially greedy agent action selection within value decomposition.
Problem
Value decomposition methods in cooperative MARL do not handle homogeneous and heterogeneous cooperative tasks simultaneously, which is needed for practical cooperative agents.
Approach
Combines value decomposition with greedy sequential execution so that agents act in a sequence, each greedily conditioned on earlier agents' actions, letting one framework cover both homogeneous and heterogeneous tasks.
Experimental setup
Baselines: value decomposition methods
Builds on: value decomposition networks QMIX
Closest papers by meaning
- Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL (AAAI 2025 · similarity 0.89)
- SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning (AAAI 2025 · similarity 0.88)
- Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.88)
- Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.87)
- Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration (NeurIPS 2024 · similarity 0.87)
- GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic (AAAI 2025 · similarity 0.87)
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.