Human-like Artificial Agents - NAIL068

• Title: Umělé bytosti
• Guaranteed by: Department of Software and Computer Science Education (32-KSVI)
• Faculty: Faculty of Mathematics and Physics
• Actual: from 2015 to 2018
• Semester: summer
• E-Credits: 6
• Hours per week, examination: summer s.:2/2, C+Ex [HT]
• Capacity: unlimited
• Min. number of students: unlimited
• 4EU+: no
• Virtual mobility / capacity: no
• State of the course: taught
• Language: Czech, English
• Teaching methods: full-time
• Teaching methods: full-time
• Note: course can be enrolled in outside the study plan; enabled for web enrollment
• Guarantor: doc. Mgr. Cyril Brom, Ph.D.
• Class: Informatika Mgr. - Teoretická informatika
• Classification: Informatics > Informatics, Software Applications, Computer Graphics and Geometry, Database Systems, Didactics of Informatics, Discrete Mathematics, External Subjects, General Subjects, Computer and Formal Linguistics, Optimalization, Programming, Software Engineering, Theoretical Computer Science, Programming, Software Engineering, Theoretical Computer Science

Annotation

English

Last update: T_KSVI (13.05.2015)

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.

Czech

Last update: T_KSVI (13.05.2015)

Umělé bytosti jsou autonomní inteligentní agenti, kteří jsou situovaní v prostředí podobném přirozenému světu a kteří se chovají podobně jako lidé nebo zvířata. Přednáška podává přehled typů umělých bytostí a jejich architektur a blíže se zabývá způsobem jejich řízení a praktickým řešením problémů spojených s částečně pozorovatelným dynamickým prostředím, které je simulované v reálném čase.

Literature

English

Last update: Mgr. Jakub Gemrot, Ph.D. (07.08.2018)

Brooks, A. R.: Intelligence without reason. In: Proceedings of the 1991 International Joint Conference on Artificial Intelligence, Sydney (1991) 569-595 

Bryson, J.: Hierarchy and sequence vs. full parallelism in reactive action selection architecture. In: From Animals to Animats (SAB00). MA. MIT Press, Cambridge (2000) 147-156

Edelstein-Keshet, L: Mathematical Models in Biology. SIAM (2005) (kap. 4.1, 4.2, 6.1 - 6.3)

Grand, S., Cliff, D., Malhotra, A.: Creatures: Artificial life autonomous software-agents for home entertainment. In: Lewis Johnson, W. (eds.): Proceedings of the First International Conference on Autonomou Agents. ACM press (1997) 22-29 

Huber, M. J.: JAM: A BDI-theoretic mobile agent architecture. In: Proceedings of the Third International Conference on Autonomous Agents (Agents'99). Seatle (1999) 236-243

Hindriks KV, (2009). Programming Rational Agents in GOAL, Multi-Agent Programming: Languages and Tools and Applications, Springer US, pages:119-157, isbn: 978-0-387-89298-6

Kokko, H.: Modelling for Field Biologists and Other Interesting People. Cambridge University Press (2007)

Laird, J. E., Newell, A., Rosenbloom, P.S.: SOAR: An Architecture for General Intelligence. In: Artificial Intelligence, 33(1) (1987) 1-64 

Mateas, M.: Interactive Drama, Art and Artificial Intelligence. Ph.D. Dissertation. Department Computer Science, Carnegie Mellon University (2002) viz též: https://eis-blog.soe.ucsc.edu/2012/02/getting-started-with-abl/

Rabin, S. (ed.): AI Game Programming Wisdom I - IV, Charles River Media (2002 - 8) 

Tyrrell, T.: Computational Mechanisms for Action Selection. Ph.D. Dissertation. Centre for Cognitive Science, University of Edinburgh (1993)

Czech

Last update: Mgr. Jakub Gemrot, Ph.D. (02.08.2018)

Brooks, A. R.: Intelligence without reason. In: Proceedings of the 1991 International Joint Conference on Artificial Intelligence, Sydney (1991) 569-595 

Bryson, J.: Hierarchy and sequence vs. full parallelism in reactive action selection architecture. In: From Animals to Animats (SAB00). MA. MIT Press, Cambridge (2000) 147-156

Edelstein-Keshet, L: Mathematical Models in Biology. SIAM (2005) (kap. 4.1, 4.2, 6.1 - 6.3)

Grand, S., Cliff, D., Malhotra, A.: Creatures: Artificial life autonomous software-agents for home entertainment. In: Lewis Johnson, W. (eds.): Proceedings of the First International Conference on Autonomou Agents. ACM press (1997) 22-29 

Huber, M. J.: JAM: A BDI-theoretic mobile agent architecture. In: Proceedings of the Third International Conference on Autonomous Agents (Agents'99). Seatle (1999) 236-243

Hindriks KV, (2009). Programming Rational Agents in GOAL, Multi-Agent Programming: Languages and Tools and Applications, Springer US, pages:119-157, isbn: 978-0-387-89298-6

Kokko, H.: Modelling for Field Biologists and Other Interesting People. Cambridge University Press (2007)

Laird, J. E., Newell, A., Rosenbloom, P.S.: SOAR: An Architecture for General Intelligence. In: Artificial Intelligence, 33(1) (1987) 1-64 

Mateas, M.: Interactive Drama, Art and Artificial Intelligence. Ph.D. Dissertation. Department Computer Science, Carnegie Mellon University (2002) viz též: https://eis-blog.soe.ucsc.edu/2012/02/getting-started-with-abl/

Rabin, S. (ed.): AI Game Programming Wisdom I - IV, Charles River Media (2002 - 8) 

Tyrrell, T.: Computational Mechanisms for Action Selection. Ph.D. Dissertation. Centre for Cognitive Science, University of Edinburgh (1993)

Syllabus

English

Last update: Mgr. Jakub Gemrot, Ph.D. (07.08.2018)

Lecture

1. Taxonomy of human-like artificial agents and applications: serious games, computer games, virtual storytelling, virtual reality, computational ethology.

2. Symbolic approaches to action selection: reactive planning, deliberative methods; if-then rules, finite-state machnies, behavioral trees, subsumption, Belief-Desire-Intention architecture, multi-layered architetures.

3. Connectionist approaches to action selection: free-flow hierarchies (Tyrrell), neural networks (Creatures, Black&White), approaches to agent learning.

4. Introduction to ethology: Psychohydraulic model of Konrad Lorenz, models of population dynamics.

5. Path-finding: path-planning, steering rules, A*, HPA*.

6. Representation of the environments: affordances, smart objects, nav-mesh, way-points, sensory versimilitude.

7. Memory: psychological classification, short-term memory & episodic memory for the agents.

8. Unified theories of cognition: Soar, ACT-R.

Practices

1. Recapitulation of Java programming language and key patterns (syntax, collections, lists, sets, maps, iterators, lazy initialization, observer pattern a its problematics, weak references), Maven basics.

2. Introduction to the Pogamut platform, Unreal Tournament 2004 (UT2004) and Unreal Engine 2 (UE2)

3. Events and objects of Pogamut virtual worlds, listeners, annotations and basics of navigation in UT2004 / UE2, introduction to BOD methodology for the development of virtual agent behaviors.

4. Steerings and movement of bots in UE2.

5. Navigation in UT2004 / UE2.

6. Visibility in UT2004 / UE2, non-trivial use of A*.

7. Items in environment of UT2004, problems connected with inperfect world representation, beliefs.

8. Weapons in environment of UT2004, weapon selection problem and "flexible latching", game domain of UT2004 Deathmatch game mode.

9. POSH action selection and BOD methodology in detail.

10. Game domain of team-oriented UT2004 Capture-the-flag game mode, team communication, role selection.

11. Example of different (non-FPS) game domain according to the interest of students (StarCraft: Brood War, Defcon, Minecraft, Super Mario, NetHack, etc.)

Czech

Last update: Mgr. Jakub Gemrot, Ph.D. (07.08.2018)

Přednáška

1. Typy umělých bytostí a aplikace: výukové simulátory, počítačové hry, seriózní hry, virtual storytelling, interaktivní drama, výpočetní etologie.

2. Řízení umělých bytostí symbolickými metodami: reaktivní plánování a deliberativní přístup; rozhodovací pravidla, konečné automaty, behaviorální stromy, subsumption architektura, BDI architektura, vícevrstvé architektury.

3. Řízení umělých bytostí konekcionistickými metodami: Tyrrellova volná hierarchie, Creatures, Black&White, problémy učení.

4. Lehký úvod do etologie. Lorenzův hydraulický model. Modely populační dynamiky.

5. Hledání cesty: steering rules, A*, HPA*.

6. Representace světa: afordance, smart objects, nav-mesh, way-points, dokonalost smyslů.

7. Paměť: klasifikace z hlediska psychologie, modely krátkodobé paměti a episodické paměti.

8. Unified theories of cognition: Soar, ACT-R.

Cvičení

1. Opakování programovacího jazyka Java (základní syntax jazyka, kolekce, listy, sety, mapy, iteratory, lazy inicializace, observer pattern a jeho problémy, slabé reference), základy Maven.

2. Úvod do platformy Pogamut, Unreal Tournament 2004 (UT2004) a Unreal Engine 2 (UE2)

3. Události a objekty virtuálního světa v Pogamutu, listenery, anotace + základy navigace v UT2004 / UE2, úvod do BOD metodologie pro návrh chování virtuálních agentů.

4. Steeringy a pohyb botů v UE2.

5. Navigace v UT2004 / UE2.

6. Viditelnost v UT2004 / UE2, netriviální použítí A*.

7. Předměty v prostředí UT2004, a problém nepřesné reprezentace světa, práce s beliefs.

8. Zbraně v prostředí UT2004, problém volby zbraně a "flexible latching", herní doména módu Deathmatch v UT2004.

9. POSH mechanismus výběru akcí a BOD metodologie podrobně.

10. Herní doména týmově orientovaného módu Capture-the-flag v UT2004.

11. Komunikace v týmu, rozdělení rolí.

12. Ochutnávka z oblasti jiné (ne FPS) herní domény (dle zájmu StarCraft: Brood War, Defcon, Minecraft, Super Mario, NetHack, aj.)