Intelligent Autonomous Agents

Recommended Prerequisites

Programming, mathematical, artificial intelligence and machine learning competencies.

Teaching Methods

The theoretical classes consist of a detailed presentation of concepts, principles, and fundamental theories of intelligent autonomous agents.

In the laboratory classes, a Project-Based Learning approach is adopted, focused on acquiring skills through practical work, involving three components: (i) analysis of works on intelligent autonomous agents described in the literature, (ii) implementation, and (iii) writing a scientific paper that describes the implementation work and can be presented and defended.

Learning Outcomes

To provide the students with advanced concepts, principles and theories required for building real world applications with agents or systems that can reason, behave or interact with their environment in an intelligent way by learning and reasoning about the real world.

Acquiring competencies in synthesis and analysis, organization and planning, written communication, problem solving, decision-making, team work, critical reasoning, autonomous learning, practical application of theoretical knowledge, and research.

Work Placement(s)

No

Syllabus

1. Agent

 

1.1 Rationality and intelligent agents

1.2 Agents, tasks, and environments

1.3 PEAS (Performance, Environment, Actuators, Sensors)

1.4 Properties of environments

1.5 Structure/Architecture and Taxonomy of agents

 

2. Multiagent System

2.1 Multi Agent Architectures

2.1 Cooperation

2.2 Collaboration

2.3 Negotiation

2.4 Communication

 

3. Uncertain Knowledge and Reasoning

3.1 Environment/world representation approaches: atomic, factored, structured

3.2 Quantification of uncertainty

3.3 Probabilistic reasoning:

 

 

4. Uncertain Knowledge and Reasoning with Temporal Dimension

4.1 Time and Uncertainty:

4.2 Transition and sensor models

4.3 Hidden Markov Models

4.4 Dynamic Bayesian Networks

 

5. Single and Complex/sequential Decision-making:

5.1 Utility Theory

5.1 Sequential decision in atomic representations: Search

5.2 Sequential decision in factored and structured representations: Planning and Markov Decision Processes

5.3 Game Theory

Assessment Methods

Assessment
Exam: 40.0%
Project: 60.0%

Bibliography

- Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th Edition). Prentice Hall.

- Wooldridge, M. (2009). An Introduction to MultiAgent Systems. John Wiley & Sons.

- Weiss, G. (2023). Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence. MIT Press.

- Albrecht, S. V., Christianos, F., & Schäfer, L. (2023). Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. MIT Press.