Results 31 to 40 of about 313 (44)

Human behaviour modelling in complex socio-technical systems : an agent based approach

, 2013
For many years we have been striving to understand human behaviour and our interactions with our socio-technological environment. By advancing our knowledge in this area, we have helped the design of new or improved work processes and technologies ...
Dugdale, Julie
core  

Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning

, 2022
In cooperative multi-agent reinforcement learning, centralized training and decentralized execution (CTDE) has achieved remarkable success. Individual Global Max (IGM) decomposition, which is an important element of CTDE, measures the consistency between
Hong, Yitian, Jin, Yaochu, Tang, Yang
core  

Personalized Federated Deep Reinforcement Learning-based Trajectory Optimization for Multi-UAV Assisted Edge Computing

, 2023
In the era of 5G mobile communication, there has been a significant surge in research focused on unmanned aerial vehicles (UAVs) and mobile edge computing technology.
Ding, Ming, Ma, Chuan, Qian, Yuwen, Song, Zhengrong, Yang, Howard H., Zhou, Xiangwei   +5 more
core  

Lenient multi-agent deep reinforcement learning [PDF]

, 2017
Much of the success of single agent deep reinforcement learning (DRL) in recent years can be attributed to the use of experience replay memories (ERM), which allow Deep Q-Networks (DQNs) to be trained efficiently through sampling stored state transitions.
Bloembergen, D. (Daniel), Palmer, G. (Gregory), Savani, R. (Rahul), Tuyls, K. (Karl)   +3 more
core  

Emergent Dominance Hierarchies in Reinforcement Learning Agents

Modern Reinforcement Learning (RL) algorithms are able to outperform humans in a wide variety of tasks. Multi-agent reinforcement learning (MARL) settings present additional challenges, and successful cooperation in mixed-motive groups of agents depends ...
Alon, Nitay, Mirsky, Reuth, Nakar, Yonatan, Rachum, Ram, Tomlinson, Bill   +4 more
core  

Emergent Cooperation under Uncertain Incentive Alignment

Understanding the emergence of cooperation in systems of computational agents is crucial for the development of effective cooperative AI. Interaction among individuals in real-world settings are often sparse and occur within a broad spectrum of ...
Acar, Erman, Grossi, Davide, Orzan, Nicole, Rădulescu, Roxana   +3 more
core  

Fully Independent Communication in Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning (MARL) comprises a broad area of research within the field of multi-agent systems. Several recent works have focused specifically on the study of communication approaches in MARL.
Artaud, Corentin, De Silva, Varuna, Liu, Xiaolan, Pina, Rafael   +3 more
core  

AI on AI: Exploring the Utility of GPT as an Expert Annotator of AI Publications

Identifying scientific publications that are within a dynamic field of research often requires costly annotation by subject-matter experts. Resources like widely-accepted classification criteria or field taxonomies are unavailable for a domain like ...
Dunham, James, Schoeberl, Christian, Toney-Wails, Autumn   +2 more
core  

Cooperative Task Execution in Multi-Agent Systems

We propose a multi-agent system that enables groups of agents to collaborate and work autonomously to execute tasks. Groups can work in a decentralized manner and can adapt to dynamic changes in the environment.
Karishma, Rao, Shrisha
core  

Backpropagation Through Agents

A fundamental challenge in multi-agent reinforcement learning (MARL) is to learn the joint policy in an extremely large search space, which grows exponentially with the number of agents.
Li, Zhiyuan, Pajarinen, Joni, Wu, Lijun, Zhao, Wenshuai   +3 more
core