Results 11 to 20 of about 139,994 (273)

Stigmergy in Multi Agent Reinforcement Learning [PDF]

open access: yesFourth International Conference on Hybrid Intelligent Systems (HIS'04), 2005
In this paper, we describe how certain aspects of the biological phenomena of stigmergy can be imported into multi-agent reinforcement learning (MARL), with the purpose of better enabling coordination of agent actions and speeding up learning. In particular, we detail how these stigmergic aspects can be used to define an inter-agent communication ...
Aras, Raghav   +2 more
openaire   +2 more sources

Kindness in Multi-Agent Reinforcement Learning

open access: yesCoRR, 2023
In human societies, people often incorporate fairness in their decisions and treat reciprocally by being kind to those who act kindly. They evaluate the kindness of others' actions not only by monitoring the outcomes but also by considering the intentions.
Farinaz Alamiyan Harandi   +2 more
openaire   +2 more sources

Mediated Multi-Agent Reinforcement Learning

open access: yesInternational Joint Conference on Autonomous Agents and Multiagent Systems, 2023
The majority of Multi-Agent Reinforcement Learning (MARL) literature equates the cooperation of self-interested agents in mixed environments to the problem of social welfare maximization, allowing agents to arbitrarily share rewards and private information.
Dmitry Ivanov   +2 more
openaire   +3 more sources

Load Frequency Control: A Deep Multi-Agent Reinforcement Learning Approach [PDF]

open access: yes, 2020
The paradigm shift in energy generation towards microgrid-based architectures is changing the landscape of the energy control structure heavily in distribution systems.
Alonso, E.   +2 more
core   +1 more source

Heterogeneous multi-Agent reinforcement learning algorithm integrating Prior-knowledge [PDF]

open access: yesZhihui kongzhi yu fangzhen, 2023
In recent years, the breakthrough of machine learning based on deep reinforcement learning provides a new development direction for intelligent game confrontation.
ZHOU Jiawei, SUN Yuxiang, XUE Yufan, XIANG Qi, WU Ying, ZHOU Xianzhong
doaj   +1 more source

Learning structured communication for multi-agent reinforcement learning

open access: yesAutonomous Agents and Multi-Agent Systems, 2022
This paper investigates multi-agent reinforcement learning (MARL) communication mechanisms in large-scale scenarios. We propose a novel framework, Learning Structured Communication (LSC), that leverages a flexible and efficient communication topology. LSC enables adaptive agent grouping to create diverse hierarchical formations over episodes generated ...
Junjie Sheng   +7 more
openaire   +3 more sources

Language Support for Multi Agent Reinforcement Learning [PDF]

open access: yesProceedings of the 13th Innovations in Software Engineering Conference (formerly known as India Software Engineering Conference), 2020
Software Engineering must increasingly address the issues of complexity and uncertainty that arise when systems are to be deployed into a dynamic software ecosystem. There is also interest in using digital twins of systems in order to design, adapt and control them when faced with such issues.
Tony Clark 0001   +3 more
openaire   +2 more sources

A proposal to use reinforcement learning to optimize decision-making in the field of counteracting money laundering and terrorist financing (Part 2)

open access: yesNowoczesne Systemy Zarządzania, 2023
Reinforcement learning focuses not only on teaching a single agent, but also the use of this method is reflected in multi-agent operation. This is an important issue from the point of view that the decision-making process and information management in ...
Maciej Aleksander Kędzierski
doaj   +1 more source

Multi-Agent Reinforcement Learning: A Survey [PDF]

open access: yes2006 9th International Conference on Control, Automation, Robotics and Vision, 2006
Multi-agent systems are rapidly finding applications in a variety of domains, including robotics, distributed control, telecommunications, economics. Many tasks arising in these domains require that the agents learn behaviors online. A significant part of the research on multi-agent learning concerns reinforcement learning techniques.
Lucian Busoniu   +2 more
openaire   +1 more source

Learning to Share in Multi-Agent Reinforcement Learning

open access: yesCoRR, 2021
ICLR 2022 Workshop on Gamification and Multiagent Solutions, Best Cooperative AI Paper ...
Yuxuan Yi   +3 more
openaire   +2 more sources

Home - About - Disclaimer - Privacy