Inhalt
[ 921PECOPCOK21 ] KV Principles of Cooperation
|
|
|
|
 |
| Workload |
Education level |
Study areas |
Responsible person |
Hours per week |
Coordinating university |
| 4,5 ECTS |
M1 - Master's programme 1. year |
Computer Science |
Ismail Khalil |
3 hpw |
Johannes Kepler University Linz |
|
|
|
| Detailed information |
| Original study plan |
Master's programme Computer Science 2025W |
| Learning Outcomes |
Competences |
| Students understand the theoretical foundations of the principles of cooperation in the context of multi-agent systems and reinforcement learning (RL), including key theoretical frameworks and models, be able to analyze and apply algorithms that facilitate cooperative behavior among agents in multi-agent environments, implement cooperative systems, evaluate practical applications and engage in research and critical discussions.
|
|
| Skills |
Knowledge |
By the end of this course, students will be able to:
- Understand the fundamental principles of cooperation and its significance in multi-agent systems. (K2)
- Apply concepts from game theory to analyze and design agent interactions. (K4, and K6)
- Implement basic and advanced reinforcement learning algorithms. (K6)
- Develop and evaluate multi-agent systems where cooperation is a critical component. (K5 and K6)
- Engage in research discussions and critically analyze contemporary literature on multi-agent cooperation. (K4 and K5)
|
- Game Theory Basics
- Multi-Agent Systems Theory
- Reinforcement Learning Fundamentals
- Cooperative Strategies
- Key RL Algorithms
- Cooperative Algorithm Variants
- Coordination Protocols
- Implementation Skills for Cooperative Systems
|
|
| Criteria for evaluation |
- Assignments: 40%
- Final Project: 50%
- Participation and Discussions: 10%
|
| Methods |
Students will work in teams (of 2-3) to design, implement, and evaluate a multi-agent system demonstrating cooperative behavior. Projects will be presented during the last week of the course.
|
| Language |
English |
| Study material |
- Axelrod, R. (1984). The Evolution of Cooperation.
- Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach
- Wooldridge, M. (2009). An Introduction to Multi-agent Systems
- VanderPlas, J. (2023). Python Data Science Handbook.
- Osborne, M. J. (2004). An Introduction to Game Theory
- Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction.
|
| Changing subject? |
No |
| Corresponding lecture |
921PECOPCOU13: UE Principles of Cooperation (1.5 ECTS) + 921PECOPCOV13: VL Principles of Cooperation (3 ECTS)
|
|
|
|
| On-site course |
| Maximum number of participants |
- |
| Assignment procedure |
Direct assignment |
|
|
|
