CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Generic animats

Claes Strannegård (Institutionen för data- och informationsteknik, Interaktionsdesign (Chalmers)) ; N. Svangård ; J. Bach ; B. Steunebrink
Lecture Notes in Computer Science - 10th International Conference on Artificial General Intelligence, AGI 2017, Melbourne, Australia, 15-18 August 2017 (0302-9743). Vol. 10414 (2017), p. 23-32.
[Konferensbidrag, refereegranskat]

We present a computational model for artificial animals (animats) living in block worlds, e.g. in Minecraft. Each animat has its individual sets of needs, sensors, and motors. It also has a memory structure that undergoes continuous development and constitutes the basis for decision-making. The mechanisms for learning and decision-making are generic in the sense that they are the same for all animats. The goal of the decision-making is always the same: to keep the needs as satisfied as possible for as long as possible. All learning is driven by surprise relating to need satisfaction. The learning mechanisms are of two kinds: (i) structural learning that adds nodes and connections to the memory structure; (ii) a local version of multi-objective Q-learning. The animats are autonomous and capable of adaptation to arbitrary block worlds without any need for seed knowledge.

Nyckelord: Autonomous agent, Dynamic graph, Multi-objective reinforcement learning, Need satisfaction, Structural learning



Denna post skapades 2017-09-13.
CPL Pubid: 251876

 

Läs direkt!


Länk till annan sajt (kan kräva inloggning)


Institutioner (Chalmers)

Institutionen för data- och informationsteknik, Interaktionsdesign (Chalmers)

Ämnesområden

Datavetenskap (datalogi)

Chalmers infrastruktur