Mastering Asymmetrical Multiplayer Game With Multi-agent Asymmetric-evolution Reinforcement Learning

Abstract

Asymmetrical multiplayer (AMP) game is a popular game genre which involves multiple types of agents competing or collaborating with each other in the game. It is difficult to train powerful agents that can defeat top human players in AMP games by typical self-play training method because of unbalancing characteristics in their asymmetrical environments. We propose asymmetric-evolution training (AET), a novel multi-agent reinforcement learning framework that can train multiple kinds of agents simultaneously in AMP game. We designed adaptive data adjustment (ADA) and environment randomization (ER) to optimize the AET process. We tested our method in a complex AMP game named Tom \& Jerry, and our AIs trained without using any human data can achieve a win rate of 98.5% against top human players over 65 matches. The ablation experiments indicated that the proposed modules are beneficial to the framework.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysun2023mastering

Related papers

• Learning From Learners: Adapting Reinforcement Learning Agents To Be Competitive In A Card Game (2020)0.00
• Game Theory And Multi-agent Reinforcement Learning : From Nash Equilibria To Evolutionary Dynamics (2024)0.00
• Policyevolve: Evolving Programmatic Policies By Llms For Multi-player Games Via Population-based Training (2025)0.00
• Neural MMO V1.3: A Massively Multiagent Game Environment For Training And Evaluating Neural Networks (2020)0.00
• Developing, Evaluating And Scaling Learning Agents In Multi-agent Environments (2022)2.26
• Inclusive Fitness As A Key Step Towards More Advanced Social Behaviors In Multi-agent Reinforcement Learning Settings (2025)0.00
• MAESTRO: Open-ended Environment Design For Multi-agent Reinforcement Learning (2023)0.00
• Multi-agent Cooperative Games Using Belief Map Assisted Training (2024)0.00