VAIN: Attentional Multi-agent Predictive Modeling
arXiv:1706.06122
Abstract
Multi-agent predictive modeling is an essential step for understanding physical, social and team-play systems. Recently, Interaction Networks (INs) were proposed for the task of modeling multi-agent physical systems, INs scale with the number of interactions in the system (typically quadratic or higher order in the number of agents). In this paper we introduce VAIN, a novel attentional architecture for multi-agent predictive modeling that scales linearly with the number of agents. We show that VAIN is effective for multi-agent predictive modeling. Our method is evaluated on tasks from challenging multi-agent prediction domains: chess and soccer, and outperforms competing multi-agent approaches.
NIPS 2017 Wrong sign fixed in Eqs:3-5
References in corpus (4)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- A simple neural network module for relational reasoning
- Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
- Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks