Skip to content

Latest commit

 

History

History
37 lines (16 loc) · 959 Bytes

File metadata and controls

37 lines (16 loc) · 959 Bytes

王者荣耀

Hierarchical Macro Strategy Model for MOBA Game AI

https://arxiv.org/pdf/1812.07887.pdf

Towards Playing Full MOBA Games with Deep Reinforcement Learning

https://arxiv.org/pdf/2011.12692.pdf

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

https://arxiv.org/ftp/arxiv/papers/2011/2011.12582.pdf

Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

AAAI2020最新论文,深度强化学习,用于王者荣耀1v1模式,cat貂蝉被人机3:0带走

https://arxiv.org/pdf/1912.09729.pdf

Learning Diverse Policies in MOBA Games via Macro-Goals

https://arxiv.org/pdf/2110.14221.pdf

Actor-Criticpolicy Optimization in a Large-Scale Imperfect-Information Game

https://openreview.net/pdf?id=DTXZqTNV5nW