• Corpus ID: 231934058

Dynamic neighbourhood optimisation for task allocation using multi-agent

  title={Dynamic neighbourhood optimisation for task allocation using multi-agent},
  author={Niall Creech and Natalia Criado and Simon Miles},
In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we… 

A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning

This survey sheds light on current approaches to tractably understanding and analyzing large-population systems, both through multi-agent reinforcement learning and through adjacent areas of research such as mean-field games, collective intelligence, or complex network theory.



Distributed task allocation in dynamic multi-agent system

The conclusion drawn from this survey is that, for dynamic multi-agent systems, the distributed task allocation is a better approach.

Task allocation for multi-agent systems in dynamic environments

This thesis explores the use coalition formation and complexity reducing mappings to accomplish task allocation for multi-agent systems in difficult environments.

Learning of coordination: exploiting sparse interactions in multiagent systems

A reinforcement learning based algorithm in which independent decision-makers/agents learn both individual policies and when and how to coordinate, and introduces a two-layer extension of Q-learning, in which each agent is augmented with a coordination action that uses information from other agents to decide the correct action.

Multi-agent distributed adaptive resource allocation (MADARA)

The multi-agent distributed adaptive resource allocation (MADARA) toolkit is presented, which is designed to address grid and cloud allocation and deployment needs and a heuristic called the comparison-based iteration by degree (CID) heuristic is presented which is used to approximate optimal deployments in MADARA.

Distributed Sensor Networks: Introduction to a Multiagent Perspective

This book is the first of its kind to examine solutions to the problem of allocating resources within such networks, in a distributed fashion, using ideas taken from the field of multiagent systems.

Reinforcement Learning With Task Decomposition for Cooperative Multiagent Systems

This article provides efficient learning-based algorithms such that each agent can learn a joint optimal policy to accomplish these multiple tasks cooperatively with other agents by using reinforcement learning (RL)-based algorithms.

A Comprehensive Survey of Multiagent Reinforcement Learning

The benefits and challenges of MARL are described along with some of the problem domains where the MARL techniques have been applied, and an outlook for the field is provided.

Solving Sparse Delayed Coordination Problems in Multi-Agent Reinforcement Learning

The techniques presented in this paper are the first to explicitly deal with a delayed reward signal when learning using sparse interactions, which allows agents to learn to take the correct action that results in the highest future reward.

Multi-agent Reinforcement Learning: An Overview

This chapter reviews a representative selection of multi-agent reinforcement learning algorithms for fully cooperative, fully competitive, and more general (neither cooperative nor competitive) tasks.

Multi-Agent Reinforcement Learning: A Review of Challenges and Applications

A detailed taxonomy of the main multi-agent approaches proposed in the literature, focusing on their related mathematical models is presented, including nonstationarity, scalability, and observability.