Hierarchical Reinforcement Learning for Multi-agent MOBA Game
This work addresses the challenge of developing effective AI agents for complex real-time strategy games, which is an incremental advancement in multi-agent reinforcement learning for gaming applications.
The paper tackled the problem of mastering Multiplayer Online Battle Arena (MOBA) games by proposing a hierarchical reinforcement learning model that combines imitation learning for macro strategies and reinforcement learning for micromanipulations, achieving a 100% win rate against bronze-level AI and creating a competitive agent for a mobile MOBA game in 5v5 mode.
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 hierarchical reinforcement learning model for mastering Multiplayer Online Battle Arena (MOBA) games, a sub-genre of RTS games. The novelty of this work are: (1) proposing a hierarchical framework, where agents execute macro strategies by imitation learning and carry out micromanipulations through reinforcement learning, (2) developing a simple self-learning method to get better sample efficiency for training, and (3) designing a dense reward function for multi-agent cooperation in the absence of game engine or Application Programming Interface (API). Finally, various experiments have been performed to validate the superior performance of the proposed method over other state-of-the-art reinforcement learning algorithms. Agent successfully learns to combat and defeat bronze-level built-in AI with 100% win rate, and experiments show that our method can create a competitive multi-agent for a kind of mobile MOBA game {\it King of Glory} in 5v5 mode.