With increasing deployment of multiple agents in complex, dynamic settings, there is an increasing need to respond to failures that occur in the agents coordination. In particular, there is need to detect and diagnose coordination failures—failures to maintain relationships between agents. We refer to this type of diagnosis as social diagnosis. Previous approaches to diagnosis in multi-agent se...

This paper proposes a new approach to multi-agent systems leveraging from recent advances in networking and reinforcement learning to scale up teamwork based on joint intentions. In this approach, teamwork is subsumed by the coordination of learning agents. The intuition behind this approach is that successful coordination at the global level generates opportunities for teamwork interactions at...

A two stage approach to co-ordination in a multi-agent society is presented. The first stage involves agents learning to co-ordinate their activities based on local and global utility – the latter being assigned by an Environment Service Node. Each agent aims to maximise its local utility over a single-step or finite horizon, subject to reinforcements being received from the ESN. An agent may r...

Multi-Agent Coordination: Theory and Applications by Jianghai Hu Doctor of Philosophy in Electrical Engineering University of California at Berkeley Professor Shankar Sastry, Chair We study the problem of optimal multi-agent coordination and related applications. The dissertation consists of three parts. In the first part, the problem of optimal coordinated motions for multiple agents moving on...

A novel style of multi-agent system specification and deployment is described, in which familiar methods from computational logic are re-interpreted to a new context. One view of multi-agent system design is that coordination is achieved via an interaction model in which participating agents assume roles constrained by the social norms of their shared task; the state of the interaction reflecti...

We describe the architecture and performance of autonomous agents that play the complex, multi-faceted internet game called Netrek. To perform competently within Netrek, an agent must be capable of 1) reacting in real-time to arcade-like tasks and environment changes within the local surroundings, 2) reasoning about strategy and long-term tasks at a slower pace and on a global scale, and 3) coo...

Coordination Artifacts are first-class software entities that encapsulate an abstract communication pattern either among Agents or between an Agent and its environment. By separating Coordination Artifacts from Agents in a Multi-Agent System (MAS), both implementations are simplified: Coordination Artifacts become an ideal means for dealing with systemic issues, while the remaining Agent code c...

Design patterns have been recently concerned in the multi-agent community for the design of systems with decentralized coordination. In this paper we present a design pattern for dealing with the complexity of developing a decentralized coordination multi-agent system for controlling a single robot. In our pattern, we combine different intelligences: an individual intelligence that enables agen...

In this paper, we review multi-agent collective behavior algorithms in the literature and classify them according to their underlying mathematical structure. For each mathematical technique, we identify the multi-agent coordination tasks it can be applied to, and we analyze its scalability, bandwidth use, and demonstrated maturity. We highlight how versatile techniques such as artificial potent...

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 ...