Multi agent systems

By Andrea Omicini, Agostino Poggi. Active Media Technology, 2005

1,020 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/21834079d92cf20ae60d8e73ee426a8a8f3c058a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Concise Introduction to Decentralized POMDPs (2016, background): “Research on MASs is motivated by the fact that it can potentially provide [Vlassis, 2007, Sycara, 1998]: • Speedup and efficiency, due to the asynchronous and parallel computation.”
Multi-objective multi-agent decision making: a utility-based analysis and survey (2019, background): “Building an intelligent distributed system is a notoriously difficult problem as it involves dealing with non-stationarity, limited resource sharing, and often requires coordination or overcoming conflicting goals [101].”
An Analysis of Agent-Based Approaches to Transport Logistics (2005, background): “Agent technology (Weiss, 1999; Wooldridge, 2002) aims to provide new concepts and abstractions to facilitate the design and implementation of systems of this kind.”
A Survey of Collectives (2004, background): “The field of Multi-Agent Systems (MAS) is concerned with the interactions among the members of such a set of agents [40, 92, 121, 204, 222], as well as the inner workings of each agent in such a set (e.”
Intelligent Information Technologies: Concepts, Methodologies, Tools and Applications (2007, methodology): “The most important reasons for using MAS when designing a system can be described as follows (Stone, 1997): • Domains with different (possibly conflicting) goals and information, where MAS is needed to handle their interactions • Having MAS could provide a method for parallel computation by…”
The Packet-World: A testbed for investigating situated multiagent systems (2005, methodology): “We use a model for action that is based on Ferber’s theory of influences and reactions [12].”
Collaborative Multiagent Reinforcement Learning by Payoff Propagation (2006, background): “A multiagent system (MAS) consists of a group of agents that reside in an environment and can potentially interact with each other (Sycara, 1998; Weiss, 1999; Durfee, 2001; Vlassis, 2003).”
Introduction to MAchine Learning & Knowledge Extraction (MAKE) (2017, background): “MAS can be traditionally characterized by the facts that (a) each agent has incomplete information and/or capabilities for solving a problem, (b) agents are autonomous, so there is no global system control; (c) data is decentralized; and (d) computation is asynchronous [98].”
Embodied Artificial Intelligence: Trends and Challenges (2003, background): “However, rather than looking for emergence, they endowed their individual agents with the same types of centralized control that they used for individuals (e.g. Ferber, 1999).”
A Roadmap of Agent Research and Development (2004, background): “Our purpose is not to provide a detailed review of the field, we leave this to others (for example, [154, 11, 74, 111, 158]).”
Multirobot systems: a classification focused on coordination (2004, methodology): “Following the literature on MAS [38], we consider Coordination as: " cooperation in which the actions performed by each robotic agent take into account the actions executed by the other robotic agents in such a way that the whole ends up being a coherent and highperformance operation " .”
On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning (2017, background): “It has been known that stateless multi-agent reinforcement learning that utilizes the softmax selection rule has close connections with the field of evolutionary game theory [9], [10], [22], [23], [54], [20], [58].”
Artificial Intelligence techniques: An introduction to their use for modelling environmental systems (2008, background): “Other difficulties in constructing MASs arise from their dynamic nature and the sophisticated interactions between agents, where goals or allocation of tasks and resources may conflict [156].”
Embracing Complexity and Uncertainty: The Potential of Agent-Based Modeling for Environmental Planning and Policy (2008, background): “Agent-based modeling has significantly contributed to the study of key parameters affecting land-use dynamics (e.g., Deadman et al., 2004; Hanley & Hopkins, 2007; Otter et al., 2001; Parker et al., 2003; Rand et al., 2002).”