Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
This addresses communication challenges in multi-agent systems for scenarios like gaming and robotics, offering a scalable solution with incremental improvements over existing methods.
The paper tackles the problem of learning when to communicate in multi-agent tasks, presenting IC3Net, which improves training efficiency and performance over baselines in cooperative, semi-cooperative, and competitive settings, with results showing enhanced convergence rates as scale increases in tasks like StarCraft.
Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Continuous Communication Model (IC3Net) which has better training efficiency than simple continuous communication model, and can be applied to semi-cooperative and competitive settings along with the cooperative settings. IC3Net controls continuous communication with a gating mechanism and uses individualized rewards foreach agent to gain better performance and scalability while fixing credit assignment issues. Using variety of tasks including StarCraft BroodWars explore and combat scenarios, we show that our network yields improved performance and convergence rates than the baselines as the scale increases. Our results convey that IC3Net agents learn when to communicate based on the scenario and profitability.