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: 2019, 2018, 2017, <=2016
This page is containing information about lectures, if you’re looking for labs info, visit Labs web page.
Follow the appropriate channel at Gamedev Discord!
Lectures: Tuesdays, 12:20, S8 (we start 18.2.2020)
Labs (two parallels): Mondays, 9:00 and 10:40, SW2 (we start 24.2.2020)
COVID-19 update: lectures happens online through Zoom, info sent separately through email and also through Discord
Plan & Slides
|1.||18.2.2020||Introduction||Cyril Brom, Jakub Gemrot||Lecture, Gardener Agent Rules, Labs Promo|
|2.||25.2.2020||Reactive Planning – Part I||Jakub Gemrot||Slides|
|3.||3.3.2020||Reactive Planning – Part II||Jakub Gemrot||Slides|
|4.||10.3.2020||Reactive Planning – Part III||Jakub Gemrot||Slides, YT|
|5.||17.3.2020||Spatial Awareness||Jakub Gemrot||Slides, YT|
|6.||24.3.2020||Steerings||Jakub Gemrot||Slides, YT|
|7.||31.3.2020||Lua language + GIT||Martin Sochor||Slides (2019)|
|8.||14.4.2020||Reactive Planning – Neural networks for action selection||Cyril Brom||NN Slides, BDI Slides (2017)|
|9.||21.4.2020||Ethology-inspired architectures for action selection
AI in Kingdome Come: Deliverance
|Cyril Brom||Ethology Slides I (2017)
Ethology Slides II (2017, in Czech)
|10.||28.4.2020||Emotions for IVAs||Michal Bída|
|12.||12.5.2020||Path-finding algorithms – Part I||Jakub Gemrot||Slides (2020), YT|
|13.||19.5.2020||Path-finding algorithms – Part II||Jakub Gemrot||Slides (2020), YT|
Terms differ according to the field you’re coming from. MFF UK students has different terms from FF UK students and vice versa. While there is also some common part for all.
Both MFF and FF UK students will be required to attend to a play testing targeting “fun aspect” of a game. Details to be filled in later and announced. Then both type of students will have an exam, but that exam will be different for MFF and FF UK students.
Exam for MFF UK Students
Exam for MFF UK students is highly practical. There will be no oral examination (unless you want it as ‘extra’) but you will have to create either a team-oriented behavior either for Pogamut 3 bots or a behavior for a NOTA robot squad. Details are available at Labs webpage.
Exam for FF UK Students
Exams for New Media Studies students: Action-selection for virtual characters: finite state machines, if-then rules, behavior trees. Navigation: A* (basic principles), steering rules, terrain representation.
Creating a 2-5 min machinima, preferably using Storyfactory tool.
Extra Notes for FF UK Students
Deadline for the script proposal: 10 April 2020.
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)