Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams

07/06/2020
by   Ankur Deka, et al.
0

Multi agent strategies in mixed cooperative-competitive environments can be hard to craft by hand because each agent needs to coordinate with its teammates while competing with its opponents. Learning based algorithms are appealing but many scenarios require heterogeneous agent behavior for the team's success and this increases the complexity of the learning algorithm. In this work, we develop a competitive multi agent environment called FortAttack in which two teams compete against each other. We corroborate that modeling agents with Graph Neural Networks and training them with Reinforcement Learning leads to the evolution of increasingly complex strategies for each team. We observe a natural emergence of heterogeneous behavior amongst homogeneous agents when such behavior can lead to the team's success. Such heterogeneous behavior from homogeneous agents is appealing because any agent can replace the role of another agent at test time. Finally, we propose ensemble training, in which we utilize the evolved opponent strategies to train a single policy for friendly agents.

READ FULL TEXT

page 3

page 4

page 5

research
03/03/2018

Model-Based Stochastic Search for Large Scale Optimization of Multi-Agent UAV Swarms

Recent work from the reinforcement learning community has shown that Evo...
research
03/24/2017

Balancing Selection Pressures, Multiple Objectives, and Neural Modularity to Coevolve Cooperative Agent Behavior

Previous research using evolutionary computation in Multi-Agent Systems ...
research
12/15/2021

Forgiveness is an Adaptation in Iterated Prisoner's Dilemma with Memory

The Prisoner's Dilemma is used to represent many real life phenomena whe...
research
05/04/2022

Creating Teams of Simple Agents for Specified Tasks: A Computational Complexity Perspective

Teams of interacting and co-operating agents have been proposed as an ef...
research
06/18/2023

Evolving Strategies for Competitive Multi-Agent Search

While evolutionary computation is well suited for automatic discovery in...
research
02/19/2019

Emergent Coordination Through Competition

We study the emergence of cooperative behaviors in reinforcement learnin...

Please sign up or login with your details

Forgot password? Click here to reset