course aims in Estonian
Kursuse eesmärk on anda üliõpilastele põhjalik arusaam tehisaru, agentide ja agentsüsteemide põhimõtetest, rakendustest ja arengutrendidest; arendada praktilisi oskusi agentsüsteemide kavandamiseks ja juurutamiseks, kasutades tänapäevaseid vahendeid ja platvorme nagu Amazone WebServices (AWS).
course aims in English
The goal of this course is to provide students with a comprehensive understanding of the principles, applications, and development trends of artificial intelligence, agents, and agentic systems; to develop practical skills for designing and implementing agentic systems using modern tools and platforms, such as AWS.
learning outcomes in the course in Est.
Õppeaine läbinud üliõpilane:
- selgitab tehisaru, intelligentse agendi ja agentsüsteemide põhialuseid ja kontseptsioone;
- analüüsib erinevaid agentsüsteemide arhitektuure ja valib sobivaid lahendusi konkreetsete probleemide lahendamiseks;
- kavandab ja rakendab agentsüsteeme, mis kasutavad suuri keelemudeleid (LLM-e) ning väliseid tööriistu (API-sid);
- rakendab masinõppe meetodeid agentsüsteemide kontekstis, et parandada nende sooritusvõimet;
- kavandab ja juurutab lihtsamaid agentsüsteeme, kasutades kaasaegseid pilvepõhiseid tööriistu ja platvorme nagu AWS;
- hindab kriitiliselt tehisintellekti ja agentsüsteemide eetilisi ning ühiskondlikke aspekte.
learning outcomes in the course in Eng.
On the successful completion of the course, the student:
- explains the fundamentals and concepts of artificial intelligence, intelligent agents, and agentic systems;
- analyzes various agentic systems architectures and chooses suitable solutions for solving specific problems;
- applies machine learning methods in the context of agentic systems to improve their performance;
- designs and implements basic agentic systems using modern cloud-based tools and platforms like AWS Academy;
- critically evaluates the ethical and societal aspects of artificial intelligence and agentic systems.
brief description of the course in Estonian
Kursus algab tehisaru ja intelligentse agendi kontseptsioonide tutvustamisega. Seejärel käsitletakse tehisaru agentsüsteemide arhitektuure ja omadusi, sealhulgas erinevaid agentide tüüpe (reaktiivsed[reactive], proaktiivsed [goal-oriented], uskumus-soov-kavatsus [belief-desire-intention] ) ning nende interaktsiooni- ja koordineerimismehhanisme. Oluline osa kursusest on pühendatud masinõppele ja selle rakendamisele agentsüsteemides, sealhulgas juhendamata õppele, juhendatud õppele ja stiimul õppele. Praktilised ülesanded keskenduvad agentsüsteemide loomisele AWS Academy platvormil, mis annab üliõpilastele reaalse kogemuse pilvepõhiste lahenduste arendamisel.
brief description of the course in English
The course begins with an introduction to the concepts of artificial intelligence and intelligent agents. It then covers the architectures and characteristics of agentic systems, including different types of agents (reactive, goal-oriented, belief-desire-intention) and their interaction and coordination mechanisms. A significant part of the course is dedicated to machine learning and its application in agentic systems, including unsupervised learning, supervised learning, and reinforcement learning. Practical assignments will focus on creating agentic systems on the AWS platform, giving students real-world experience in developing cloud-based solutions.
type of assessment in Estonian
Suuline eksam.
type of assessment in English
Oral exam.
independent study in Estonian
-
independent study in English
-
study literature
- Russell, S. J. & Norvig, P. (2020). Artificial Intelligence: A Modern Approach. 4th Edition. Pearson.
- Wooldridge, M. (2009). An Introduction to MultiAgent Systems. 2nd Edition. John Wiley & Sons.
- M. J. Mataric. (2007). The Robotics Primer. The MIT Press.
- E. Alpaydin. (2020). Introduction to Machine Learning. 4th Edition. The MIT Press.
- Biswas, W. Talukdar (2025) Building Agentic AI Systems. Packt Publishing
- M. Lanham (2025) AI Agents in Action. Manning Publications
study forms and load
daytime study: weekly hours
4.0
session-based study work load (in a semester):