可扩展性
计算机科学
盈利能力指数
趋同(经济学)
分布式计算
多样性(控制论)
比例(比率)
钥匙(锁)
简单(哲学)
人工智能
计算机安全
认识论
数据库
物理
量子力学
经济增长
哲学
经济
财务
作者
Amanpreet Singh,Tushar Jain,Sainbayar Sukhbaatar
出处
期刊:Cornell University - arXiv
日期:2018-09-27
被引量:26
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI