Natural Emergence Of Heterogeneous Strategies In Artificially Intelligent Competitive Teams

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydeka2020natural

Related papers

• Mimicking To Dominate: Imitation Learning Strategies For Success In Multiagent Competitive Games (2023)0.00
• Learning Heterogeneous Agent Cooperation Via Multiagent League Training (2022)7.16
• Emergent Coordination Through Competition (2019)0.00
• Multi-agent Actor-critic For Mixed Cooperative-competitive Environments (2017)0.00
• The Impact Of Behavioral Diversity In Multi-agent Reinforcement Learning (2024)0.00
• Two-stage Training Algorithm For AI Robot Soccer (2021)0.00
• Multi-agent Deep Reinforcement Learning With Human Strategies (2018)8.09
• All By Myself: Learning Individualized Competitive Behaviour With A Contrastive Reinforcement Learning Optimization (2023)7.16