Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games

no code implementations • 21 May 2021 • Won Joon Yun, Sungwon Yi, Joongheon Kim

In real-time strategy (RTS) game artificial intelligence research, various multi-agent deep reinforcement learning (MADRL) algorithms are widely and actively used nowadays.

Graph Attention Reinforcement Learning (RL) +2