Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning

2023-04-20 · Chenglu Sun, Yichi Zhang, Yu Zhang, Ziling Lu, Jingbin Liu, Sijia Xu, Weidong Zhang

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.

📄 PDF Abstract BibTeX arXiv:2304.10124

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning reinforcement-learning

Methods 이 논문이 사용한 방법론

AMP Based on the understanding that the flat local minima of the empirical risk cause the model to generalize better. Adversarial Model Perturbation (AMP) improves generalization via…

Hierarchical Macro Strategy Model for MOBA Game AI

2018-12-19 · Bin Wu, Qiang Fu, Jing Liang, Peng Qu 외

The next challenge of game AI lies in Real Time Strategy (RTS) games. RTS games provide partially observable gaming environments, where agents interact with one another in an action space much larger than that of GO. Mas…

Hierarchical Reinforcement Learning for Multi-agent MOBA Game

2019-01-23 · Zhijian Zhang, Haozheng Li, Luo Zhang, Tianyin Zheng 외

Real Time Strategy (RTS) games require macro strategies as well as micro strategies to obtain satisfactory performance since it has large state space, action space, and hidden information. This paper presents a novel hie…

Hierarchical Reinforcement Learning Imitation Learning reinforcement-learning Reinforcement Learning+2

Evolutionary Game-Theoretical Analysis for General Multiplayer Asymmetric Games

2022-06-22 · Xinyu Zhang, Peng Peng, Yushan Zhou, Haifeng Wang 외

Evolutionary game theory has been a successful tool to combine classical game theory with learning-dynamical descriptions in multiagent systems. Provided some symmetric structures of interacting players, many studies hav…

Starcraft Starcraft II

Parallel Algorithm for Approximating Nash Equilibrium in Multiplayer Stochastic Games with Application to Naval Strategic Planning

2019-10-01 · Sam Ganzfried, Conner Laughlin, Charles Morefield

Many real-world domains contain multiple agents behaving strategically with probabilistic transitions and uncertain (potentially infinite) duration. Such settings can be modeled as stochastic games. While algorithms have…

Navigating the Landscape of Multiplayer Games

2020-05-04 · Shayegan Omidshafiei, Karl Tuyls, Wojciech M. Czarnecki, Francisco C. Santos 외

Multiplayer games have long been used as testbeds in artificial intelligence research, aptly referred to as the Drosophila of artificial intelligence. Traditionally, researchers have focused on using well-known games to …