Joint Attention for Multi-Agent Coordination and Social Learning

2021-04-15 · Dennis Lee, Natasha Jaques, Chase Kew, Jiaxing Wu, Douglas Eck, Dale Schuurmans, Aleksandra Faust

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.

📄 PDF Abstract BibTeX arXiv:2104.07750

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningInductive BiasReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Coordinate attention Hou et al. proposed coordinate attention, a novel attention mechanism which embeds positional information into channel attention, so that the network can focus on large…

InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs

2025-12-08 · Bin Li, Ruichi Zhang, Han Liang, Jingyan Zhang 외 arxiv

Humanoid agents are expected to emulate the complex coordination inherent in human social behaviors. However, existing methods are largely confined to single-agent scenarios, overlooking the physically plausible interpla…

Resolving Implicit Coordination in Multi-Agent Deep Reinforcement Learning with Deep Q-Networks & Game Theory

2020-12-08 · Griffin Adams, Sarguna Janani Padmanabhan, Shivang Shekhar

We address two major challenges of implicit coordination in multi-agent deep reinforcement learning: non-stationarity and exponential growth of state-action space, by combining Deep-Q Networks for policy learning with Na…

Deep Reinforcement Learning OpenAI Gym Reinforcement Learning (RL)

Future-Interactions-Aware Trajectory Prediction via Braid Theory

2026-03-23 · Caio Azevedo, Stefano Sabatini, Sascha Hornauer, Fabien Moutarde arxiv

To safely operate, an autonomous vehicle must know the future behavior of a potentially high number of interacting agents around it, a task often posed as multi-agent trajectory prediction. Many previous attempts to mode…

Trajectory Prediction

CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making

2026-05-02 · Guowei Zou, Haitao Wang, Beiwen Zhang, Boning Zhang 외 arxiv

Generative models have emerged as a promising paradigm for offline multi-agent reinforcement learning (MARL), but existing approaches require many iterative sampling steps. Recent few-step acceleration methods either dis…

Multi-agent Reinforcement Learning Decision Making

DSDF: An approach to handle stochastic agents in collaborative multi-agent reinforcement learning

2021-09-14 · Satheesh K. Perepu, Kaushik Dey

Multi-Agent reinforcement learning has received lot of attention in recent years and have applications in many different areas. Existing methods involving Centralized Training and Decentralized execution, attempts to tra…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)