Reward-sharing Relational Networks In Multi-agent Reinforcement Learning As A Framework For Emergent Behavior

Abstract

In this work, we integrate `social' interactions into the MARL setup through a user-defined relational network and examine the effects of agent-agent relations on the rise of emergent behaviors. Leveraging insights from sociology and neuroscience, our proposed framework models agent relationships using the notion of Reward-Sharing Relational Networks (RSRN), where network edge weights act as a measure of how much one agent is invested in the success of (or `cares about') another. We construct relational rewards as a function of the RSRN interaction weights to collectively train the multi-agent system via a multi-agent reinforcement learning algorithm. The performance of the system is tested for a 3-agent scenario with different relational network structures (e.g., self-interested, communitarian, and authoritarian networks). Our results indicate that reward-sharing relational networks can significantly influence learned behaviors. We posit that RSRN can act as a framework where differen

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyhaeri2022reward

Related papers

• Social Influence As Intrinsic Motivation For Multi-agent Deep Reinforcement Learning (2018)0.00
• Robust Multi-agent Reinforcement Learning With Social Empowerment For Coordination And Communication (2020)0.00
• Learning To Share In Multi-agent Reinforcement Learning (2021)0.00
• Achieving Collective Welfare In Multi-agent Reinforcement Learning Via Suggestion Sharing (2024)0.00
• Influence-based Reinforcement Learning For Intrinsically-motivated Agents (2021)0.00
• Impact Of Relational Networks In Multi-agent Learning: A Value-based Factorization View (2023)0.00
• REMAX: Relational Representation For Multi-agent Exploration (2020)2.26
• Fully Decentralized Multi-agent Reinforcement Learning With Networked Agents (2018)0.00