Learning Systems Engineering

2005 ◽  
pp. 1820-1826
Author(s):  
Valentina Plekhanova
Keyword(s):  
Machine Learning ◽  
Systems Engineering ◽  
Autonomous Agents ◽  
Single Agent ◽  
Learning System ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Agent Learning ◽  
Multi Agent ◽  
Conventional Machine

Traditionally multi-agent learning is considered as the intersection of two subfields of artificial intelligence: multi-agent systems and machine learning. Conventional machine learning involves a single agent that is trying to maximise some utility function without any awareness of existence of other agents in the environment (Mitchell, 1997). Meanwhile, multi-agent systems consider mechanisms for the interaction of autonomous agents. Learning system is defined as a system where an agent learns to interact with other agents (e.g., Clouse, 1996; Crites & Barto, 1998; Parsons, Wooldridge & Amgoud, 2003). There are two problems that agents need to overcome in order to interact with each other to reach their individual or shared goals: since agents can be available/unavailable (i.e., they might appear and/or disappear at any time), they must be able to find each other, and they must be able to interact (Jennings, Sycara & Wooldridge, 1998).

Learning Systems Engineering

2011 ◽  
pp. 1429-1438
Author(s):  
Valentina Plekhanova
Keyword(s):  
Machine Learning ◽  
Systems Engineering ◽  
Autonomous Agents ◽  
Single Agent ◽  
Learning System ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Agent Learning ◽  
Multi Agent ◽  
Conventional Machine

Traditionally multi-agent learning is considered as the intersection of two subfields of artificial intelligence: multi-agent systems and machine learning. Conventional machine learning involves a single agent that is trying to maximise some utility function without any awareness of existence of other agents in the environment (Mitchell, 1997). Meanwhile, multi-agent systems consider mechanisms for the interaction of autonomous agents. Learning system is defined as a system where an agent learns to interact with other agents (e.g., Clouse, 1996; Crites & Barto, 1998; Parsons, Wooldridge & Amgoud, 2003). There are two problems that agents need to overcome in order to interact with each other to reach their individual or shared goals: since agents can be available/unavailable (i.e., they might appear and/or disappear at any time), they must be able to find each other, and they must be able to interact (Jennings, Sycara & Wooldridge, 1998).

scholarly journals Multiparty Dynamics and Failure Modes for Machine Learning and Artificial Intelligence

2019 ◽  
Vol 3 (2) ◽  
pp. 21 ◽  
Author(s):  
David Manheim
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Failure Modes ◽  
Single Agent ◽  
Multi Agent Systems ◽  
Coordination Failures ◽  
Agent Systems ◽  
Important Challenge ◽  
Multi Agent ◽  
Distributional Shifts

An important challenge for safety in machine learning and artificial intelligence systems is a set of related failures involving specification gaming, reward hacking, fragility to distributional shifts, and Goodhart’s or Campbell’s law. This paper presents additional failure modes for interactions within multi-agent systems that are closely related. These multi-agent failure modes are more complex, more problematic, and less well understood than the single-agent case, and are also already occurring, largely unnoticed. After motivating the discussion with examples from poker-playing artificial intelligence (AI), the paper explains why these failure modes are in some senses unavoidable. Following this, the paper categorizes failure modes, provides definitions, and cites examples for each of the modes: accidental steering, coordination failures, adversarial misalignment, input spoofing and filtering, and goal co-option or direct hacking. The paper then discusses how extant literature on multi-agent AI fails to address these failure modes, and identifies work which may be useful for the mitigation of these failure modes.

Machine Learning for Agents and Multi-Agent Systems

2011 ◽  
pp. 1-26
Author(s):  
Daniel Kudenko ◽  
Dimitar Kazakov ◽  
Eduardo Alonso
Keyword(s):  
Machine Learning ◽  
Autonomous Agents ◽  
Machine Learning Techniques ◽  
Multi Agent Systems ◽  
Learning Agents ◽  
Agent Systems ◽  
Learning Techniques ◽  
Comprehensive Survey ◽  
Multi Agent ◽  
The Relationship

In order to be truly autonomous, agents need the ability to learn from and adapt to the environment and other agents. This chapter introduces key concepts of machine learning and how they apply to agent and multi-agent systems. Rather than present a comprehensive survey, we discuss a number of issues that we believe are important in the design of learning agents and multi-agent systems. Specifically, we focus on the challenges involved in adapting (originally disembodied) machine learning techniques to situated agents, the relationship between learning and communication, learning to collaborate and compete, learning of roles, evolution and natural selection, and distributed learning. In the second part of the chapter, we focus on some practicalities and present two case studies.

Machine Learning for Agents and Multi-Agent Systems

2011 ◽  
pp. 403-420
Author(s):  
Daniel Kudenko ◽  
Dimitar Kazakov ◽  
Eduardo Alonso
Keyword(s):  
Machine Learning ◽  
Autonomous Agents ◽  
Machine Learning Techniques ◽  
Multi Agent Systems ◽  
Learning Agents ◽  
Agent Systems ◽  
Learning Techniques ◽  
Comprehensive Survey ◽  
Multi Agent ◽  
The Relationship

In order to be truly autonomous, agents need the ability to learn from and adapt to the environment and other agents. This chapter introduces key concepts of machine learning and how they apply to agent and multi-agent systems. Rather than present a comprehensive survey, we discuss a number of issues that we believe are important in the design of learning agents and multi-agent systems. Specifically, we focus on the challenges involved in adapting (originally disembodied) machine learning techniques to situated agents, the relationship between learning and communication, learning to collaborate and compete, learning of roles, evolution and natural selection, and distributed learning. In the second part of the chapter, we focus on some practicalities and present two case studies.

Cooperative Behavior Learning Based on Social Interaction of State Conversion and Reward Exchange Among Multi-Agents

2011 ◽  
Vol 15 (5) ◽  
pp. 606-616 ◽  
Author(s):  
Kun Zhang ◽  
◽  
Yoichiro Maeda ◽  
Yasutake Takahashi ◽  
Keyword(s):  
Social Interaction ◽  
Autonomous Agents ◽  
Cooperative Behavior ◽  
Single Agent ◽  
Multi Agent Systems ◽  
Related Individual ◽  
Agent Systems ◽  
Behavior Learning ◽  
Multi Agent ◽  
Multi Agents

In multi-agent systems, it is necessary for autonomous agents to interact with each other in order to have excellent cooperative performance. Therefore, we have studied social interaction between agents to see how they acquire cooperative behavior. We have found that sharing environmental states can improve agent cooperation through reinforcement learning, and that changing environmental states to target-related individual states improves cooperation. To further improve cooperation, we propose reward redistribution based on reward exchanges among agents. In receiving rewards from both the environment and other agents, agents learned how to adjust themselves to the environment and how to explore and strengthen cooperation in tasks that a single agent could not do alone. Agents thus cooperate best through the interaction of state conversion and reward exchange.

scholarly journals A Programming Approach to Collective Autonomy

2021 ◽  
Vol 10 (2) ◽  
pp. 27
Author(s):  
Roberto Casadei ◽  
Gianluca Aguzzi ◽  
Mirko Viroli
Keyword(s):  
Autonomous Vehicles ◽  
Autonomic Computing ◽  
Autonomous Agents ◽  
Programming Approach ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Multi Agent ◽  
Simulated Case ◽  
Complex Settings

Research and technology developments on autonomous agents and autonomic computing promote a vision of artificial systems that are able to resiliently manage themselves and autonomously deal with issues at runtime in dynamic environments. Indeed, autonomy can be leveraged to unburden humans from mundane tasks (cf. driving and autonomous vehicles), from the risk of operating in unknown or perilous environments (cf. rescue scenarios), or to support timely decision-making in complex settings (cf. data-centre operations). Beyond the results that individual autonomous agents can carry out, a further opportunity lies in the collaboration of multiple agents or robots. Emerging macro-paradigms provide an approach to programming whole collectives towards global goals. Aggregate computing is one such paradigm, formally grounded in a calculus of computational fields enabling functional composition of collective behaviours that could be proved, under certain technical conditions, to be self-stabilising. In this work, we address the concept of collective autonomy, i.e., the form of autonomy that applies at the level of a group of individuals. As a contribution, we define an agent control architecture for aggregate multi-agent systems, discuss how the aggregate computing framework relates to both individual and collective autonomy, and show how it can be used to program collective autonomous behaviour. We exemplify the concepts through a simulated case study, and outline a research roadmap towards reliable aggregate autonomy.

scholarly journals Group Behavior Learning in Multi-Agent Systems Based on Social Interaction Among Agents

2011 ◽  
Vol 15 (7) ◽  
pp. 896-903 ◽  
Author(s):  
Kun Zhang ◽  
◽  
Yoichiro Maeda ◽  
Yasutake Takahashi ◽  
Keyword(s):  
Social Interaction ◽  
Autonomous Agents ◽  
Cooperative Behavior ◽  
Group Behavior ◽  
Learning Ability ◽  
Human Beings ◽  
Multi Agent Systems ◽  
Agent Systems ◽  
Multi Agent ◽  
State Of The Environment

Research on multi-agent systems, in which autonomous agents are able to learn cooperative behavior, has been the subject of rising expectations in recent years. We have aimed at the group behavior generation of the multi-agents who have high levels of autonomous learning ability, like that of human beings, through social interaction between agents to acquire cooperative behavior. The sharing of environment states can improve cooperative ability, and the changing state of the environment in the information shared by agents will improve agents’ cooperative ability. On this basis, we use reward redistribution among agents to reinforce group behavior, and we propose a method of constructing a multi-agent system with an autonomous group creation ability. This is able to strengthen the cooperative behavior of the group as social agents.

Sign in / Sign up

Export Citation Format

Share Document