Multi-Agent Systems by Incremental Gradient Reinforcement Learning
نویسندگان
چکیده
A new reinforcement learning (RL) methodology is proposed to design multi-agent systems. In the realistic setting of situated agents with local perception, the task of automatically building a coordinated system is of crucial importance. We use simple reactive agents which learn their own behavior in a decentralized way. To cope with the difficulties inherent to RL used in that framework, we have developed an incremental learning algorithm where agents face more and more complex tasks. We illustrate this general framework on a computer experiment where agents have to coordinate to reach a global goal.
منابع مشابه
Multi-Agent Learning with Policy Prediction
Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting the basic gradient ascent approach with policy prediction. We prove that this augmentation results in a stronger notion of convergence than the basic gradient ascent, that is, strategies converge to a Nash equilibrium wi...
متن کاملVoltage Coordination of FACTS Devices in Power Systems Using RL-Based Multi-Agent Systems
This paper describes how multi-agent system technology can be used as the underpinning platform for voltage control in power systems. In this study, some FACTS (flexible AC transmission systems) devices are properly designed to coordinate their decisions and actions in order to provide a coordinated secondary voltage control mechanism based on multi-agent theory. Each device here is modeled as ...
متن کاملMulti-agent Learning and the Reinforcement Gradient
The number of proposed reinforcement learning algorithms appears to be ever-growing. This article tackles the diversification by showing a persistent principle in several independent reinforcement learning algorithms that have been applied to multi-agent settings. While their learning structure may look very diverse, algorithms such as Gradient Ascent, Cross learning, variations of Q-learning a...
متن کاملCooperative Multi-agent Control Using Deep Reinforcement Learning
This work considers the problem of learning cooperative policies in complex, partially observable domains without explicit communication. We extend three classes of single-agent deep reinforcement learning algorithms based on policy gradient, temporal-difference error, and actor-critic methods to cooperative multi-agent systems. We introduce a set of cooperative control tasks that includes task...
متن کاملIntelligent Systems in Nanjing University
Intelligent systems is a major research theme in Nanjing University, with the support from the State Key Laboratory for Novel Software Technology of China, one of the top laboratories in the information technology field in the whole country. Currently, the research carried out by the intelligent systems group at Nanjing University mainly fo-cuses on the following topics: • Fundamental methods o...
متن کامل