Introduction to Intelligent Autonomous Systems

Code:

CC3042

Acronym:

CC3042

Level:

300

Keywords
Classification	Keyword
OFICIAL	Computer Science

Instance: 2022/2023 - 1S

Active?	Yes
Responsible unit:	Department of Computer Science
Course/CS Responsible:	Bachelor in Artificial Intelligence and Data Science

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
L:IACD	2	study plan from 2021/22	3	-	6	56	162

Teaching language

Suitable for English-speaking students

Objectives

This Unit presents a global perspective of the techniques associated with intelligent and autonomous systems, exploring the modeling and simulation of complex systems and the development of applications of intelligent agents and Multi-Agent Systems with the ability to adapt / learn to solve complex problems. The main objective is to specify and implement autonomous, complex and adaptive intelligent systems. At the end of the course, students should be able to:
1. Understand basic concepts related to autonomous intelligent systems and be able to model and design complex intelligent and autonomous systems.
2. Understand and be able to use the concept of reinforcement learning, including state of the art algorithms and deep reinforcement learning mechanisms.
3. Understand and be able to use concepts of intelligent multi-agent systems such as communication, interaction, coordination, negotiation and cooperation

Learning outcomes and competences

Ability to specify and implement autonomous, complex and adaptive intelligent systems.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Knowledge of Python Programming and Artificial Intelligence.

Program

1. Intelligent Autonomous Systems: Intelligent Systems; Agents; Multi-Agent Systems
2. Machine Learning Autonomous Systems: Markov Decision Processes and Partially Observable MDPs; Model-Based/Model Free Solution methods; Reinforcement Learning (RL); Exploration vs Exploitation; Deep Reinforcement Learning; RL Algorithms: Q-Learning, SARSA; SAC and PPO.
3. Multi-Agent Systems: Concept; Architectures; Communication; Interaction; Coordination; Negotiation; Teamwork; Game Theory; Multi-Agent Planning

Mandatory literature

Stuart Jonathan Russell; Artificial intelligence. ISBN: 978-1-292-40113-3

Teaching methods and learning activities

Oral presentation of the themes of the course in theoretical classes, with interaction with students. Tool experimentation and exploration and exercise solving in the practical classes. Practical classes will also be based on the supervision of assignments. Project-oriented learning. Students develop a simple but complete project during the course.

Evaluation Type

Distributed evaluation without final exam

Assessment Components

designation	Weight (%)
Exame	50,00
Trabalho prático ou de projeto	50,00
Total:	100,00

Amount of time allocated to each course unit

designation	Time (hours)
Estudo autónomo	56,00
Frequência das aulas	56,00
Trabalho laboratorial	50,00
Total:	162,00

Eligibility for exams

Terms of frequency: Enrolled students must not exceed the allowed number of non-attendance to lab classes and achieve a minimum grade of 7.5 (out of 20) in the practical assignment and a mean of 7.5 in the 2 eamxs/tests.

Calculation formula of final grade

Type of evaluation: Distributed evaluation without final exam.

2 Exams/Tests: T1 with weight 25% and T2 with weight 25%.

Practical Worw (PW), with weight 50% and the following evaluation components: 20% * Midterm Presentation + 40% * Project Code & Demo + 20% * Final Report + 20% * Final Presentation.

Final Grade = 0.25*T1+0.25*T2+0.5*PW

In the case of Exam, it counts for 50% of the final grade. 

The exam grade can be improved in the appeal period. The practical part cannot be improved.

Examinations or Special Assignments

N/A

Internship work/project

Special assessment (TE, DA, ...)

Students with special circumstances should discuss and negotiate their situation with the responsible of the course.

Classification improvement

The exam grade can be improved in the appeal period. The practical part cannot be improved.

Observations

Jury:

Luis Paulo Reis
Alípio Jorge
Álvaro Figueira