Attention-based communication for multi-agent reinforcement learning

Speaker(s)

Maciej Wojtala

Affiliation

University of Warsaw

Language of the talk

English

Date

March 27, 2025, 12:15 p.m.

Room

room 4050

Title in Polish

Attention-based communication for multi-agent reinforcement learning

Seminar

Seminar Games, Mechanisms, and Social Networks

---

In multi-agent reinforcement learning, problems that attract most 
research include action-value function decomposition and inter-agent 
communication. In most studies, these problems are addressed separately. 
In this paper, we introduce the aggregation of messages from all agents 
in a central unit and the broadcast of the combined information to all 
the agents. Our proposed central unit can be easily added to existing 
architectures of action-value decomposition. Due to the use of attention 
in the central unit, it contains a number of trainable weights 
independent of the number of agents. In the experimental study with 
Foraging and SMAC2, our proposed approach yields encouraging results.

---