Strategic Capability-Learning for Improved Multiagent Collaboration in Ad Hoc Environments

Jumadinova, Janyl; Dasgupta, Prithviraj; Soh, Leen-Kiat

doi:10.1109/tsmc.2013.2285527

Cited by 13 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jamroga, Meski, and Szreter (2013) define the degree of openness of multi-agency as the complexity of the minimal transformation that the system must undergo in order to add a new agent to the system or remove an existing one from the system. Jumadinova et al (2014) and Chen et al (2015) extend the notion of openness to include both agent openness and task openness to model the dynamic nature of the agents and tasks in the system. They consider both fluctuations in the availability of agents needed to perform tasks, as well as dynamic changes in the type of tasks that appear over time.…”

Section: Initial Discussionmentioning

confidence: 99%

“…Task openness (Jumadinova et al 2014;Chen et al 2015) occurs when the set of tasks that agents can work on change over time as new tasks are introduced and prior tasks disappear, which manifests in many real-world applications. This is common in situations where agents may assume new roles and thus acquire a different set of tasks to accomplish (e.g., promotion or transfer within a company), or where the environment undergoes changes from one phase to another (e.g., driving in the city followed by driving in the interstate).…”

Section: Task Opennessmentioning

confidence: 99%

See 1 more Smart Citation

Decision making in open agent systems

Eck,

Soh,

Doshi

2023

AI Magazine

View full text Add to dashboard Cite

In many real‐world applications of AI, the set of actors and tasks are not constant, but instead change over time. Robots tasked with suppressing wildfires eventually run out of limited suppressant resources and need to temporarily disengage from the collaborative work in order to recharge, or they might become damaged and leave the environment permanently. In a large business organization, objectives and goals change with the market, requiring workers to adapt to perform different sets of tasks across time. We call these multiagent systems (MAS) open agent systems (OASYS), and the openness of the sets of agents and tasks necessitates new capabilities and modeling for decision making compared to planning and learning in closed environments. In this article, we discuss three notions of openness: agent openness, task openness, and type openness. We also review the past and current research on addressing the novel challenges brought about by openness in OASYS. We share lessons learned from these efforts and suggest directions for promising future work in this area. We also encourage the community to engage and participate in this area of MAS research to address critical real‐world problems in the application of AI to enhance our daily lives.

show abstract

Section: Initial Discussionmentioning

confidence: 99%

Section: Task Opennessmentioning

confidence: 99%

Decision making in open agent systems

Eck,

Soh,

Doshi

2023

AI Magazine

View full text Add to dashboard Cite

show abstract

“…Researchers [10,4] have identified task openness as a further type of openness in MAS, beyond agent openness, to capture changes in the tasks. In the same context, the authors in [19] define MAS openness as the ability of the system to adapt itself to uncertainty in the environment and to handle dynamic perturbations like the coming of new tasks and resources.…”

Section: Related Background 21 Opennessmentioning

confidence: 99%

A biologically inspired computational trust model for open multi-agent systems which is resilient to unwillingness and dishonesty in reporting of trust information

Lygizou

Kalles

2023

Preprint

View full text Add to dashboard Cite

Selfish agents in highly dynamic and open multi-agent systems are usually unwilling to exchange information with each another and usually dishonest when doing so. Thus, the use of trust information provided by other agents makes most trust and reputation systems susceptible to various sorts of disinformation. To deal with this issue, we have proposed a computational trust model from the perspective of the trustee, inspired by aspects of the synaptic plasticity of the brain, in which the trustor does not choose a trustee to delegate a task, but it is the trustee who decides whether it has the skills to perform the task or not. The proposed trust model follows the decentralized approach, it is developed so as to deal with the requirements of highly dynamic and open multi-agent systems, and since agents do not exchange trust information, it is immune to various sorts of disinformation. We conducted an extensive empirical evaluation of our model comparing it with FIRE, an established trust and reputation model for open multi-agent systems, and observed that our model was able to perform consistently in various dynamic conditions, maintaining a high level of utility gain for the agents and being immune to unwillingness and dishonesty in reporting of trust information.

show abstract

“…To solve the problem of distributed collaboration among multiple agents, Jumadinova et al [15] proposed a learning technique based on human learning theory, enabling an agent to select appropriate capabilities to learn from other agents. e result shows that the overall utility of agents is significantly improved.…”

Section: Related Workmentioning

confidence: 99%

Multiagent Light Field Reconstruction and Maneuvering Target Recognition via GAN

Luo

Cai

Zhou

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The lack of sample data and the limited visual range of a single agent during light field reconstruction affect the recognition of maneuvering targets. In view of the above problems, this paper introduces generative adversarial nets (GAN) into the field of light field reconstruction and proposes a multiagent light field reconstruction and target recognition method based on GAN. The algorithm of this paper utilizes the characteristics of GAN to generate data and enhance data, which greatly improves the accuracy of light field reconstruction. The consistency mean of all observations is obtained by multiagent data fusion, which ensures the reliability of sample data and the continuity of maneuvering target recognition. The experimental results show that the accuracy of light field reconstruction reaches 94.552%. The accuracy of maneuvering target recognition is 84.267%, and the more the agents are used, the shorter the recognition time.

show abstract

Strategic Capability-Learning for Improved Multiagent Collaboration in Ad Hoc Environments

Cited by 13 publications

References 13 publications

Decision making in open agent systems

Decision making in open agent systems

A biologically inspired computational trust model for open multi-agent systems which is resilient to unwillingness and dishonesty in reporting of trust information

Multiagent Light Field Reconstruction and Maneuvering Target Recognition via GAN

Contact Info

Product

Resources

About