Hierarchical control of multi-agent reinforcement learning team in real-time strategy (RTS) games

作者：

Highlights：

• A hierarchical Command and Control model of RL agents for Real-Time Strategy Game.

• The model enables the unit’s individual decisions while directed by a commander agent.

• A self-organizing neural network realizes the agents at strategic and unit level.

• Empirical works demonstrate the model’s flexibility in achieving agents’ coordination.

摘要

•A hierarchical Command and Control model of RL agents for Real-Time Strategy Game.•The model enables the unit’s individual decisions while directed by a commander agent.•A self-organizing neural network realizes the agents at strategic and unit level.•Empirical works demonstrate the model’s flexibility in achieving agents’ coordination.

论文关键词：Hierarchical control,Self-organizing neural networks,Reinforcement learning,Real-time strategy games

论文评审过程：Received 21 March 2021, Revised 2 July 2021, Accepted 31 July 2021, Available online 11 August 2021, Version of Record 1 September 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115707