ALMA: Hierarchical Learning For Composite Multi-agent Tasks

Abstract

Despite significant progress on multi-agent reinforcement learning (MARL) in recent years, coordination in complex domains remains a challenge. Work in MARL often focuses on solving tasks where agents interact with all other agents and entities in the environment; however, we observe that real-world tasks are often composed of several isolated instances of local agent interactions (subtasks), and each agent can meaningfully focus on one subtask to the exclusion of all else in the environment. In these composite tasks, successful policies can often be decomposed into two levels of decision-making: agents are allocated to specific subtasks and each agent acts productively towards their assigned subtask alone. This decomposed decision making provides a strong structural inductive bias, significantly reduces agent observation spaces, and encourages subtask-specific policies to be reused and composed during training, as opposed to treating each new composition of subtasks as unique. We intr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyiqbal2022alma

Related papers

• Strategic Coordination For Evolving Multi-agent Systems: A Hierarchical Reinforcement And Collective Learning Approach (2025)0.00
• Learning Complex Teamwork Tasks Using A Given Sub-task Decomposition (2023)0.00
• Hierarchical Deep Multiagent Reinforcement Learning With Temporal Abstraction (2018)0.00
• Learning To Advise And Learning From Advice In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• LDSA: Learning Dynamic Subtask Assignment In Cooperative Multi-agent Reinforcement Learning (2022)3.58
• Guiding Multi-agent Multi-task Reinforcement Learning By A Hierarchical Framework With Logical Reward Shaping (2024)0.00
• Individual Specialization In Multi-task Environments With Multiagent Reinforcement Learners (2019)0.00
• Multi-agent Continual Coordination Via Progressive Task Contextualization (2023)5.24