ROMA: Multi-Agent Reinforcement Learning with Emergent Roles

03/18/2020
by   Tonghan Wang, et al.
0

The role concept provides a useful tool to design and understand complex multi-agent systems, which allows agents with a similar role to share similar behaviors. However, existing role-based methods use prior domain knowledge and predefine role structures and behaviors. In contrast, multi-agent reinforcement learning (MARL) provides flexibility and adaptability, but less efficiency in complex tasks. In this paper, we synergize these two paradigms and propose a role-oriented MARL framework (ROMA). In this framework, roles are emergent, and agents with similar roles tend to share their learning to be specialized on certain sub-tasks. To this end, we construct a stochastic role embedding space by introducing two novel regularizers and conditioning individual policies on roles. Experiments show that our method can learn dynamic, versatile, identifiable, and specialized roles, which help our method push forward the state of the art on the StarCraft II micromanagement benchmark. Demonstrative videos are available at https://sites.google.com/view/romarl/.

READ FULL TEXT

page 1

page 5

page 6

page 7

page 14

page 16

research
03/18/2020

Multi-Agent Reinforcement Learning with Emergent Roles

The role concept provides a useful tool to design and understand complex...
research
01/31/2023

Learning Roles with Emergent Social Value Orientations

Social dilemmas can be considered situations where individual rationalit...
research
12/14/2022

Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning

Adequate strategizing of agents behaviors is essential to solving cooper...
research
02/28/2022

Pippi: Practical Protocol Instantiation

A protocol specifies interactions between roles, which together constitu...
research
04/17/2023

About latent roles in forecasting players in team sports

Forecasting players in sports has grown in popularity due to the potenti...
research
05/03/2023

System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning

Evolutionary science provides evidence that diversity confers resilience...
research
04/03/2023

Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles

Role-based learning is a promising approach to improving the performance...

Please sign up or login with your details

Forgot password? Click here to reset