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

Abstract

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.

IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Dota 2 with Large Scale Deep Reinforcement Learning
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• StarCraft II: A New Challenge for Reinforcement Learning
• Playing FPS Games with Deep Reinforcement Learning
• Learning Longer-term Dependencies in RNNs with Auxiliary Losses
• Distilling Policy Distillation
• The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI
• MOBA: a New Arena for Game AI
• Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
• MOBA-Slice: A Time Slice Based Evaluation Framework of Relative Advantage between Teams in MOBA Games

Cited by in corpus (4)

• TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations
• Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning
• Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
• Boosting Offline Reinforcement Learning with Residual Generative Modeling