Syllabus
1. Taxonomy of human-like artificial agents and applications: serious games, computer games, virtual storytelling, virtual reality.
2. Architectures: behavioural, functional/cognitive, connectionists. Static and dynamic worlds.
3. Symbolic approach to action selection: hierarchical reactive planning, deliberative methods; if-then rules, finite-state machnies; architectures: subsumption, BDI, multi-layered.
4. Connectionism: free-flow hierarchies (Tyrrell), neural networks (Creatures, Black&White), learning, ethological minimum, neurobiological minimum.
5. Path-finding: path-planning, steering rules.
6. Representation of the environments: affordances, smart objects, smart actions, nav-mesh, way-points, sensory versimilitude.
7. Artificial emotions: Champandard, OOC.
8. Memory: pszchological classification, short-term memory & episodic memory for the agents.
9. Artificial evolution: introduction.
10. Unified theories of cognition: Soar, ACT-R.
Annotation
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 topic of artificial emotions will be studied as well.