Alert button
Picture for Zhijian Zhang

Zhijian Zhang

Alert button

Hierarchical Reinforcement Learning for Multi-agent MOBA Game

Jan 23, 2019
Zhijian Zhang, Haozheng Li, Luo Zhang, Tianyin Zheng, Ting Zhang, Xiong Hao, Xiaoxin Chen, Min Chen, Fangxu Xiao, Wei Zhou

Figure 1 for Hierarchical Reinforcement Learning for Multi-agent MOBA Game
Figure 2 for Hierarchical Reinforcement Learning for Multi-agent MOBA Game
Figure 3 for Hierarchical Reinforcement Learning for Multi-agent MOBA Game
Figure 4 for Hierarchical Reinforcement Learning for Multi-agent MOBA Game

Although deep reinforcement learning has achieved great success recently, there are still challenges in Real Time Strategy (RTS) games. Due to its large state and action space, as well as hidden information, RTS games require macro strategies as well as micro level manipulation to obtain satisfactory performance. In this paper, we present a novel hierarchical reinforcement learning model for mastering Multiplayer Online Battle Arena (MOBA) games, a sub-genre of RTS games. In this hierarchical framework, agents make macro strategies by imitation learning and do micromanipulations through reinforcement learning. Moreover, we propose a simple self-learning method to get better sample efficiency for reinforcement part and extract some global features by multi-target detection method in the absence of game engine or API. In 1v1 mode, our agent successfully learns to combat and defeat 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 King of Glory (KOG) in 5v5 mode.

* 7 pages, 7 figures 
Viaarxiv icon