pith. sign in

arxiv: 2104.07750 · v2 · pith:KMTJC4RZnew · submitted 2021-04-15 · 💻 cs.AI · cs.MA

Joint Attention for Multi-Agent Coordination and Social Learning

classification 💻 cs.AI cs.MA
keywords attentionjointagentscoordinationlearningmulti-agentabilitysocial
0
0 comments X
read the original abstract

Joint attention - the ability to purposefully coordinate attention with another agent, and mutually attend to the same thing -- is a critical component of human social cognition. In this paper, we ask whether joint attention can be useful as a mechanism for improving multi-agent coordination and social learning. We first develop deep reinforcement learning (RL) agents with a recurrent visual attention architecture. We then train agents to minimize the difference between the attention weights that they apply to the environment at each timestep, and the attention of other agents. Our results show that this joint attention incentive improves agents' ability to solve difficult coordination tasks, by reducing the exponential cost of exploring the joint multi-agent action space. Joint attention leads to higher performance than a competitive centralized critic baseline across multiple environments. Further, we show that joint attention enhances agents' ability to learn from experts present in their environment, even when completing hard exploration tasks that do not require coordination. Taken together, these findings suggest that joint attention may be a useful inductive bias for multi-agent learning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Toward Virtuous Reinforcement Learning: A Critique and Roadmap

    cs.AI 2025-12 unverdicted novelty 5.0

    The paper argues for modeling ethics in RL as relatively stable habits and dispositions rather than rules or scalar rewards, and provides a four-part roadmap using social learning, multi-objective methods, regularizat...