Self Organizing Multiagent Systems

Credits
4.5
Types
Optional
Requirements
This subject has not requirements , but it has got previous capacities
Department
UB;CS
Web
https://raco.fib.upc.edu/home/assignatura?espai=270742
Mail
maite_lopez@ub.edu
Self-Organising Agent Systems builds on students' prior knowledge of multi-agent systems (MAS) to explore their capacity for autonomous adaptation. The course revisits the foundational concepts of agents and agent societies, then moves into Agent-Based Social Simulation (ABSS) and the principles of self-organisation and adaptation, incorporating elements of ethics and Multi-Agent Reinforcement Learning (MARL). The course concludes by examining the relationship between MAS and the emerging field of Agentic AI, where agents powered by Large Language Models (LLMs) are capable of autonomous planning, tool use, and interaction within complex environments.

By the end of the course, students will be able to identify applications suited to agent-oriented solutions, understand how these systems adapt and self-organise, and connect classical MAS principles to modern LLM-based agentic architectures.

Teachers

Person in charge

  • Maite López Sánchez (maite_lopez@ub.edu)

Weekly hours

Theory
1.3
Problems
1
Laboratory
0.7
Guided learning
0.12
Autonomous learning
5.55

Competences

Generic Technical Competences

Generic

  • CG3 - Capacity for modeling, calculation, simulation, development and implementation in technology and company engineering centers, particularly in research, development and innovation in all areas related to Artificial Intelligence.

    • Technical Competences of each Specialization

    Academic

  • CEA1 - Capability to understand the basic principles of the Multiagent Systems operation main techniques , and to know how to use them in the environment of an intelligent service or system.
  • CEA7 - Capability to understand the problems, and the solutions to problems in the professional practice of Artificial Intelligence application in business and industry environment.
  • CEA9 - Capability to understand Multiagent Systems advanced techniques, and to know how to design, implement and apply these techniques in the development of intelligent applications, services or systems.

    • Professional

  • CEP2 - Capability to solve the decision making problems from different organizations, integrating intelligent tools.
  • CEP3 - Capacity for applying Artificial Intelligence techniques in technological and industrial environments to improve quality and productivity.
  • CEP4 - Capability to design, write and report about computer science projects in the specific area of ??Artificial Intelligence.

    • Transversal Competences

    Teamwork

  • CT3 - Ability to work as a member of an interdisciplinary team, as a normal member or performing direction tasks, in order to develop projects with pragmatism and sense of responsibility, making commitments taking into account the available resources.

    • Information literacy

  • CT4 - Capacity for managing the acquisition, the structuring, analysis and visualization of data and information in the field of specialisation, and for critically assessing the results of this management.

    • Analisis y sintesis

  • CT7 - Capability to analyze and solve complex technical problems.

    • Objectives

    1. Learning objectives referring to knowledge:
      Related competences: CT4, CT7, CEA1, CEP2, CEP4, CEA9, CEA7,
      Subcompetences
      • To be familiar with the ethical/moral aspects associated with autonomous systems.
      • To be familiar with alternative agents' social models and interaction behaviours.
      • To understand how multi-agent systems use norms to coordinate, and how they can be adapted.
      • To be introduced to Multi-Agent Reinforcement Learning methods.
      • To be aware of possible applications of multi-agent technologies and agent-based simulation.
    2. Objectives referring to abilities, skills:
      Students will acquire the capacity to determine which applications are compatible with the implementation of agent-oriented solutions and how these solutions can adapt automatically to periodic changes.
      They will also become able to develop simulations of multi-agent systems and analyse how they perform globally.
      Related competences: CEP3, CG3,
    3. Objectives referring to attitudes, values and norms:
      Students will develop teamwork skills and will reflect on ethical / moral aspects associated to autonomous systems.
      Related competences: CT3,

    Contents

    1. Introduction to multi-agent systems
      * Cooperative vs competitive agents, * Social models, * Organizations * Institutions * Applications
    2. Agent-based simulation
      * Individual modelling, * Social analysis, * Tools & case studies
    3. Adaptation and coordination
      * Normative Multi-Agent systems * Moral agents * Multi-Agent Reinforcement Learning.
    4. MAS and the emerging field of Agentic AI
      Analysis of the relationship between MAS and the emerging field of Agentic AI, where agents powered by Large Language Models (LLMs) are capable of autonomous interaction within complex environments.

    Activities

    Activity Evaluation act


    Presentation and discussion of a research paper


    Objectives: 1
    Contents:
    Theory
    6h
    Problems
    0h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    22.2h

    Course practical assessment


    Objectives: 1 2 3
    Contents:
    Theory
    2h
    Problems
    0h
    Laboratory
    9.1h
    Guided learning
    0h
    Autonomous learning
    40h

    Theoretical knowledge acquisition


    Objectives: 1
    Contents:
    Theory
    8.5h
    Problems
    13h
    Laboratory
    0h
    Guided learning
    1.6h
    Autonomous learning
    10h

    Teaching methodology

    The course unit will be taught through a series of theory and practical sessions:

    - Participatory theory sessions in which new concepts are introduced and discussed between students. Group discussion is strongly encouraged. Textbook chapters and research papers will be provided to facilitate debate and exchange of ideas.

    - Practical sessions in which students put into practice previously introduced concepts to gain further insight. This objective will be achieved by solving problems, designing systems, and developing prototypes.

    As far as possible, the gender perspective will be incorporated in the development of the subject. In addition, the teaching staff will be attentive to those specific gender needs that the students may raise, such as being able to choose a partner of the same gender if group work is carried out or being able to pose challenges against the gender gap.

    Evaluation methodology

    Students will be assessed on in-class oral presentations and/or their work in practical assignments. Typically, marks for oral presentations will be awarded on an individual basis, whereas marks for practical assignments will be based on an assessment of the whole group. The weighting of the final grade will be proportional to the respective workloads of the two tasks.

    Examination-based assessment: Students will submit a practical exercise for assessment at the end of the course unit.

    Bibliography

    Basic

    Complementary

    Web links

    Previous capacities

    It will help to know about MAS (Multi-Agent Systems)