RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning

no code implementations • 2 Jun 2022 • Hao Chen, Guangkai Yang, Junge Zhang, Qiyue Yin, Kaiqi Huang

Specifically, these methods do not explicitly utilize the relationship between agents and cannot adapt to different sizes of inputs.

Reinforcement Learning (RL) Relation +1