Generic animats
Paper i proceeding, 2017

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.

Dynamic graph

Autonomous agent

Need satisfaction

Multi-objective reinforcement learning

Structural learning


Claes Strannegård

Chalmers, Tillämpad informationsteknologi, Interaktionsdesign (Chalmers)

N. Svangård

Göteborgs universitet

J. Bach

Harvard University

B. Steunebrink


Lecture Notes in Computer Science

0302-9743 (ISSN)

Vol. 10414 23-32


Datavetenskap (datalogi)