Joint Attention for Multi-Agent Coordination and Social Learning

04/15/2021
by   Dennis Lee, et al.
14

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.

READ FULL TEXT

page 7

page 13

page 14

research
06/19/2020

Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) requires coordination to effic...
research
10/01/2020

Learning Social Learning

Social learning is a key component of human and animal intelligence. By ...
research
05/27/2023

Attention Schema in Neural Agents

Attention has become a common ingredient in deep learning architectures....
research
10/31/2020

FireCommander: An Interactive, Probabilistic Multi-agent Environment for Joint Perception-Action Tasks

The purpose of this tutorial is to help individuals use the FireCommande...
research
06/01/2022

DM^2: Distributed Multi-Agent Reinforcement Learning for Distribution Matching

Current approaches to multi-agent cooperation rely heavily on centralize...
research
03/23/2021

Spatial Intention Maps for Multi-Agent Mobile Manipulation

The ability to communicate intention enables decentralized multi-agent r...
research
10/04/2022

Meta Navigation Functions: Adaptive Associations for Coordination of Multi-Agent Systems

In this paper, we introduce a new class of potential fields, i.e., meta ...

Please sign up or login with your details

Forgot password? Click here to reset