Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

By Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li and 8 more. 2020

60 citations recorded by the source corpus.

We present JueWu-SL, the first supervised-learning-based artificial intelligence (AI) program that achieves human-level performance in playing multiplayer online battle arena (MOBA) games. Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner. Tested on Honor of Kings, the most popular MOBA at present, our AI performs competitively at the level of High King players in standard 5v5 games.

Subfields: Artificial Intelligence, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mingfei Sun
2. Katja Hofmann
3. Jun Zhu
4. Sam Devlin
5. Tim Pearce
6. Deheng Ye
7. David Bignell
8. Fengming Zhu

In Sociology and Political Science

1. Jun Zhu
2. Tabish Rashid

Citations in the corpus

• TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations (2021, positive): “2 Accelerate Multi-agent Reinforcement Learning Training Preivous work (Silver et al., 2016; Vinyals et al., 2019; Ye et al., 2020) shows that pre-trained supervised models help a lot for the follow-up deep reinforcement learning training.”
• Imitating Human Behaviour with Diffusion Models (2023, background): “More specifically, Behaviour Cloning (BC), despite being theoretically limited (Ross et al., 2011), has been empirically effective in domains such as autonomous driving (Pomerleau, 1991), robotics (Florence et al., 2022) and game playing (Ye et al., 2020; Pearce and Zhu, 2022).”