In this course, we will study human-like artificial agents, that is autonomous intelligent agents situated in a virtual environment similar to real world that act like humans. The course gives an overview of types of such agents and their architectures with the emphasis on the problem of action selection. The course also focuses on solving practical issues related to real-time and partially observable environments. The course is taught at MFF UK as NAIL068.
History: 2022, 2021, 2020, 2019, 2018, 2017, <=2016
This page is containing information about lectures, if you’re looking for labs info, visit Labs web page.
News
Follow the appropriate channel at Gamedev Discord!
https://discord.gg/c49DHBJ
Dates (SIS)
Lectures: Tuesdays, 17:20, SW2
Form: Combination of self-studying from supplied slides and videos combined with questionnaires and Q/A live sessions
Invited talks: There will be a live-session block (of 2×90 minutes) given by Adam Streck during the last 4 weeks of the semester
Start: 14.2.2022, 17:20, SW2
Plan & Slides
No. | Date | Topic | Lecturer | Form | Materials |
1. | 14.2.2023 (Tue) |
Introduction | Jakub Gemrot | IRL meet in SW2 w/ course organization info |
Slides: -1-, -2-, -3- Videos: -1-, -2-, -3- |
2. | 21.2.2023 (Tue) |
Reactive Planning – Part I – If-then and alikes | Jakub Gemrot | Self-study | PDF (2022), MP4 (2021) |
28.2.2023 (Tue) |
Cancelled | Jakub Gemrot | |||
3. | 7.3.2023 (Tue) |
Spatial Awareness | Jakub Gemrot | Self-study | PDF (2020), YT (2020) |
14.3.2023 (Tue) |
Cancelled | ||||
4. | 21.3.2023 (Tue) |
Live Q/A Session | Jakub Gemrot | IRL in SW2 | Questionnaire 1 Questionnaire 2 |
Steerings | Jakub Gemrot | Self-study | PDF (2023) YT (2020) |
||
5. | 28.3.2023 (Tue) |
Reactive Planning – Part II – Finite State Machines | Jakub Gemrot | Self-study | PDF (2022) MP4 (2022) |
6. | 5.4.2023 (Wed) |
Reactive Planning – Part III – Behavior trees | Jakub Gemrot | Self-study | PDF (2022) MP4 (2022) |
7.. | 12.4.2023 (Wed) |
Live Q/A Session | Jakub Gemrot | IRL in SW2 | Questionnaire 3 Questionnaire 4 Question-pad |
8. | 18.4.2023 (Tue) |
Agent-based Modelling | Adam Streck | IRL in SW2 | PDF (2023) |
9. | 19.4.2023 (Wed) |
Agent-based Learning | Adam Streck | IRL in SW2 | PDF (2023) |
10. | 26.4.2023 (Wed) |
Path-finding – Part I | Jakub Gemrot | Self-study | PDF (2020) YT (2020) |
11. | 3.5.2023 (Web) |
Path-finding – Part II | Jakub Gemrot | Self-study | PDF (2020) YT (2020) |
12. | 9.5.2023 (Tue) | Creating a Virtual Human(-oid) | Adam Streck | IRL in S4 | GSlides (2023) |
Grading
Exam for will have two parts: 1) test-powered exam, 2) practical assignment, in which you will have to create either a team-oriented behavior either for Pogamut 3 bots or a behavior for a NOTA robot squad.
The final grade will be determined by the amount of points you will gather throughout the course.
These points are gained from:
- T = Test-powered exam, max. 40 points;
- L = Labs-final practical assignment (either in Pogamut 3 or NOTA, your choice), max. 90 points;
- A = Advanced points gathered from from homeworks, here you will take either points from Pogamut 3 or NOTA (not both!), max. 40 points;
- Note that in Pogamut 3 track you can also gain extra points from scoring in Tournaments, but the cap is 40 points still.
- Final Score = T + Max{Lp+Ap, Ln+An}
Final Scoring | Final Grade |
[0-90) | Fail |
[90-105) | C |
[105-120) | B |
[120-170] | A |
State Final Exam
Breakdown of the Multi-agent systems state final exam topics (pre 2020/21):
- Autonomous agent architectures; agent perception, agent action selection mechanism, agent memory.
- Covered by lectures in NAIL069 (on reactive planning and neural networks) and NAIL106
- Psychological inspiration.
- Covered by BDI and Emotion slides in the archive below
- Methods for agent control; symbolic and connectionist reactive planning, hybrid approaches.
- Dtto 1+2 plus concrete examples of algorithms / mechanisms for agent control
- Path search problem, steering rules, terrain representation.
- Covered by NAIL069, concretely lectures on Spatial Awareness, Steerings and the Path-finding algorithms – Part I
- Communication and knowledge in multiagent systems, ontologies, speech acts, FIPA-ACL, protocols. Distributed problem solving, cooperation, Nash equilibria, Pareto efficiency, source allocation, auctions. Agent design methodologies, agent languages and environments.
- Covered mostly by NAIL106
- Ethological inspiration, models of population dynamics. Methods for agent learning; reinforcement learning, basic forms of animal learning.
- David J. Sweatt: Mechanisms of memory, Elsevier Academic Press, 2003 ch. 1 (Elsevier)
- Notes on Chaining
- Notes on Shaping
- Richard S. Sutton and Andrew G. Barto: Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA (1998) ch.1-7 (PDF)
Follows the list of other recommended literature:
- Michael Wooldridge: An Introduction to MultiAgent Systems. Willey (2002) 1st ed. or 2nd ed. (Wiley)
- Supplementary: Gerhard Weiss (editor): Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence. (základy: kap 1)
- Hanna Kokko: Modelling For Field Biologists and Other Interesting People. Cambridge University Press (2007) ch. 1, 2, 7, 8 (Amazon)
- Leah Edelstein-Keshet: Mathematical Models in Biology. SIAM (2005) ch. 4.1, 4.2, 6.1-6.3 (Epubs)
- Melanie Mitchell: An Introduction to Genetic Algorithms, MIT Press, 1996 (1st ed), 1998 (2nd ed). ch. 1-4 (Amazon)
- David E. Goldberg: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Pub. Co. 1989. (kap. 1–4)
- Steve Rabin (ed.): AI Game Programming Wisdom I, Charles River Media, 2002 ch. 4.3 (PDF)
- Steve Rabin (ed.): AI Game Programming Wisdom IV, Charles River Media, 2008 ch. 2.2, 2.3, 2.5, 2.6 (Amazon)
Slides Archive (2010-2015)
- Introduction (in Czech)
- Reactive planning, If-then rules, Finite state machines, POSH (updated 130227)
- Pathfinding (in Czech)
- Steering (updated spring 2012)
- Creatures, neural networks, evolutionary algorithms
- Tyrrell (free-flow hierarchy)
- Computational ethology (in Czech)
- Fuzzy approach, emotions (Champandard)
- Belief Desire Intention
- Representation – logic, RETE, affordances, deictic representation
- Agents vs. Animats, Wooldridge, FIPA, speech acts
- Soar intro
- Storytelling intro
- Spatial memory & psychological experiments (updated 130425)
- Slides on emotions (2007, in Czech)