IJCAI-95 Workshop on Adaptation and Learning in Multiagent Systems (original) (raw)
Related papers
Machine Learning for Agents and Multi-Agent Systems
2003
ABSTRACT 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 multiagent 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.
Multiagent Learning within a collaborative environment
2012
Multiagent Learning is at the intersection of multiagent systems and Machine Learning, two subdomains of artificial intelligence. Traditional Machine Learning technologies usually imply a single agent that is trying to maximize some utility functions without having any knowledge about other agents within its environment. The multiagent systems domain refers to the domains where several agents are involved and mechanisms for the independent agents’ behaviors interaction have to be considered. Due to multiagent systems’ complexity, there have to be found solutions for using Machine Learning technologies to manage this complexity.
Learning and adaption in multiagent systems
1997
Abstract The goal of a self-interested agent within a multiagent system is to maximize its utility over time. In a situation of strategic interdependence, where the actions of one agent may affect the utilities of other agents, the optimal behavior of an agent must be conditioned on the expected behaviors of the other agents in the system.
Problems of learning in multi-agent systems
1998
Multi-agent systems are usually very complex in their structure and functionality. In most of the application tasks, it iS,difficult or sometimes impossible to determine exactly and correctly behavior and activities of a multi-agent system during its design. Therefore it is important to [md a way how to improve system's activity during its operation. This can be achieved by leaming agents which modify their behaviour according to their experience. There have to be studied and developed new methods of machine leaming which will prove useful for this purpose. The paper reviews the basic problems of learning in multi-agent systems and some approaches applied for their solution.
Incremental and Mutual Adaptation in Multiagent Systems
1999
There are two streams of research when combining multiagent systems and learning. One regards multiagent systems in which the agents have learning capabilities and they learn from the environment in which they operate. The feedback the agent receives from the environment includes knowledge about the other agents in the system. The second direction investigates the issue of multiagent learning where the focus is on the interactions among the learning agents. Each agent learns directly from the other agents that operate in the same environment.
Using a Machine Learning Approach To Support an Intelligent Cooperative Multi-Agent System
In this paper, we describe a machine learning approach, ID3 Decision Tree Induction Algorithm, to analyzing and predicting learning style of learners on-line. Our goal is to adapt the interaction by choosing an appropriate presentation for the learners. One way to make a good adaptation is by extracting some knowledge about each learner such as learners' behavior during a learning session, knowledge level, and learning styles. We have developed a Confidence Intelligent Tutoring System (CITS), which is based on a multi-agent approach, in order to manage negotiations within a community of learners. The main goal of CITS is to adapt intelligent distance learning environments interactions among the participants to be more cooperative. This paper focuses on how CITS can extract the knowledge from learners. An experiment shows that this approach can determine learning style with 78% accuracy. Using this way, CITS can predict learning style instead of using a long questionnaire.
Lecture Notes in Computer Science, 2012
This book contains the papers accepted for presentation at the 2011 edition of the Adaptive and Learning Agents (ALA) workshop. ALA is the result of the merger of the ALAMAS and ALAg workshops. ALAMAS was an annual European workshop on Adaptive and Learning Agents and Multi-Agent Systems, held eight times. ALAg was the international workshop on Adaptive and Learning agents, typically held in conjunction with AAMAS. To increase the strength, visibility, and quality of the workshops, ALAMAS and ALAg were combined into the ALA workshop, and a steering committee was appointed to guide its development.
Self-adaptation using multiagent systems
2010
Abstract Each decade has its key software technology to advance artificial intelligence, and each technology is highlighted in a novel that sells much better than the underlying technology. Who hasn't read Michael Crichton's Prey and wondered how far multiagent systems might evolve and how they might affect humankind? Our technology column digs into this topic in this issue.