Human-like Artificial Agents (Summer 2017/2018)

Contents

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.

Permalink: http://bit.ly/mff-uk-hlaa-lecture-2018

History: 2017<=2016

This page is containing information about lectures, if you’re looking for labs info, visit Labs web page.


Dates (SIS)

Lectures: Tuesdays, 10:40, S4 (we start 20.2.2018)

Labs (two parallels): Mondays, 9:00, SW1 (we start 19.2.2018) and Tuesdays, 15:40, SW1 (we start 20.2.2018)


Plan & Slides

No. Date Topic Lecturer Slides
1. 20.2.2018 Introduction Cyril Brom, Jakub Gemrot Lecture, Gardener Agent Rules, Labs Promo
2. 27.2.2018 Reactive Planning – Part I Jakub Gemrot PDF
3. 6.3.2018 Reactive Planning – Part II Jakub Gemrot PDF
4. 13.3.2018 Reactive Planning – Part III Jakub Gemrot PDF
5. 20.3.2017 Reactive Planning – Neural networks for action selection Cyril Brom 2017 (old):
NN Slides, BDI Slides
6. 27.3.2017 Cancelled
7. 3.4.2018 Spatial Awareness Jakub Gemrot Environment representation
Steerings
8. 10.4.2018 Ethologically inspired architectures for action selection I Cyril Brom 2017 (old):
Ethology Slides I
9. 17.4.2018 Ethologically inspired architectures for action selection II
AI in Kingdome Come: Deliverance
Cyril Brom 2017 (old):
Ethology Slides II
 (in Czech)
10. 24.4.2018 Emotions for IVAs Michal Bída PDF
1.5.2018 National holiday
8.5.2018 National holiday
11. 15.5.2018 Steerings Jakub Gemrot PDF
 12. 22.5.2018 Selected theses from the Seminar
– Combat in Children of the Galaxy
– PCG: Rogue-like Dungeon
– DQN and Angry Birds
– PCG: Endless runner games
Pavel Šmejkal
Ondřej Nepožítek
Katya Nikonová
Vojtěch Černý
Combat in Children of the Galaxy
PCG: Rogue-like Dungeon
DQN and Angry Birds
PCG: Endless runner games

Exam

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.


Experiment (for both MFF & FF UK students)

The experiment is mandatory only for Czech-speaking students.

  1. Please, make sure Java is installed at your system
  2. Ensure that you have at least 45 minutes of time (without interrupts)
  3. Open the link of the Experiment
  4. Follow the steps in there
  5. In the end, send an email to Vojtěch Černý (woitee@gmail.com) informing him that you have finished the experiment and watch out for the confirmations

Deadline: 18.5.2018


Slides Archive (2010-2015)

  1. Introduction (in Czech)
  2. Reactive planning, If-then rules, Finite state machines, POSH (updated 130227)
  3. Pathfinding (in Czech)
  4. Steering (updated spring 2012)
  5. Creatures, neural networks, evolutionary algorithms
  6. Tyrrell (free-flow hierarchy)
  7. Computational ethology (in Czech)
  8. Fuzzy approach, emotions (Champandard)
  9. Belief Desire Intention
  10. Representation – logic, RETE, affordances, deictic representation
  11. Agents vs. Animats, Wooldridge, FIPA, speech acts
  12. Soar intro
  13. Storytelling intro
  14. Spatial memory & psychological experiments (updated 130425)
  15. Slides on emotions (2007, in Czech)

https://gamedev.cuni.cz/wp-content/uploads/2018/10/logolink_OP_VVV_hor_barva_eng.jpg