Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior

07/12/2022
by   Hossein Haeri, et al.
0

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 different relational networks produce distinct emergent behaviors, often analogous to the intuited sociological understanding of such networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/30/2019

Multi-Agent Adversarial Inverse Reinforcement Learning

Reinforcement learning agents are prone to undesired behaviors due to re...
research
11/17/2018

Parameter Sharing Reinforcement Learning Architecture for Multi Agent Driving Behaviors

Multi-agent learning provides a potential framework for learning and sim...
research
01/20/2022

Safety-Aware Multi-Agent Apprenticeship Learning

Our objective of this project is to make the extension based on the tech...
research
10/05/2021

Influencing Towards Stable Multi-Agent Interactions

Learning in multi-agent environments is difficult due to the non-station...
research
01/18/2014

Location-Based Reasoning about Complex Multi-Agent Behavior

Recent research has shown that surprisingly rich models of human activit...
research
09/28/2020

Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks

This work proposes a neural network architecture that learns policies fo...
research
05/12/2023

Multi-Agent Reinforcement Learning for Network Routing in Integrated Access Backhaul Networks

We investigate the problem of wireless routing in integrated access back...

Please sign up or login with your details

Forgot password? Click here to reset