Separation Of Concerns In Reinforcement Learning

Abstract

In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task. This approach has two main advantages: 1) it allows for training specialized agents on different parts of the task, and 2) it provides a new way to transfer knowledge, by transferring trained agents. Our framework generalizes the traditional hierarchical decomposition, in which, at any moment in time, a single agent has control until it has solved its particular subtask. We illustrate our framework with empirical experiments on two domains.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyvanseijen2016separation

Related papers

• Deep Decentralized Multi-task Multi-agent Reinforcement Learning Under Partial Observability (2017)0.00
• Revisiting The Master-slave Architecture In Multi-agent Deep Reinforcement Learning (2017)0.00
• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• Learning Complex Teamwork Tasks Using A Given Sub-task Decomposition (2023)0.00
• ALMA: Hierarchical Learning For Composite Multi-agent Tasks (2022)0.00
• Learning From Multiple Independent Advisors In Multi-agent Reinforcement Learning (2023)0.00
• Multi-task Multi-agent Shared Layers Are Universal Cognition Of Multi-agent Coordination (2023)0.00
• Individual Specialization In Multi-task Environments With Multiagent Reinforcement Learners (2019)0.00