Claes Strannegård, Abdul Rahim Nizamani, Jonas Juel and Ulf Persson
In the story Alice in Wonderland, Alice fell down a rabbit hole and suddenly found herself in a strange world called Wonderland. Alice gradually developed knowledge about Wonderland by observing, learning, and reasoning. In this paper we present the system Alice In Wonderland that operates analogously. As a theoretical basis of the system, we define several basic concepts of logic in a generalized setting, including the notions of domain, proof, consistency, soundness, completeness, decidability, and compositionality. We also prove some basic theorems about those generalized notions. Then we model Wonderland as an arbitrary symbolic domain and Alice as a cognitive architecture that learns autonomously by observing random streams of facts from Wonderland. Alice is able to reason by means of computations that use bounded cognitive resources. Moreover, Alice develops her belief set by continuously forming, testing, and revising hypotheses. The system can learn a wide class of symbolic domains and challenge average human problem solvers in such domains as propositional logic and elementary arithmetic.
Claes Strannegård, Wen Xu, Niklas Engsner and John A. Endler
Although animals such as spiders, fish, and birds have very different anatomies, the basic mechanisms that govern their perception, decision-making, learning, reproduction, and death have striking similarities. These mechanisms have apparently allowed the development of general intelligence in nature. This led us to the idea of approaching artificial general intelligence (AGI) by constructing a generic artificial animal (animat) with a configurable body and fixed mechanisms of perception, decision-making, learning, reproduction, and death. One instance of this generic animat could be an artificial spider, another an artificial fish, and a third an artificial bird. The goal of all decision-making in this model is to maintain homeostasis. Thus actions are selected that might promote survival and reproduction to varying degrees. All decision-making is based on knowledge that is stored in network structures. Each animat has two such network structures: a genotype and a phenotype. The genotype models the initial nervous system that is encoded in the genome (“the brain at birth”), while the phenotype represents the nervous system in its present form (“the brain at present”). Initially the phenotype and the genotype coincide, but then the phenotype keeps developing as a result of learning, while the genotype essentially remains unchanged. The model is extended to ecosystems populated by animats that develop continuously according to fixed mechanisms for sexual or asexual reproduction, and death. Several examples of simple ecosystems are given. We show that our generic animat model possesses general intelligence in a primitive form. In fact, it can learn simple forms of locomotion, navigation, foraging, language, and arithmetic.
Claes Strannegård, Nils Svangård, David Lindström, Joscha Bach and Bas Steunebrink
A computational model for artificial animals (animats) interacting with real or artificial ecosystems is presented. All animats use the same mechanisms for learning and decisionmaking. Each animat has its own set of needs and its own memory structure that undergoes continuous development and constitutes the basis for decision-making. The decision-making mechanism aims at keeping the needs of the animat as satisfied as possible for as long as possible. Reward and punishment are defined in terms of changes to the level of need satisfaction. The learning mechanisms are driven by prediction error relating to reward and punishment and are of two kinds: multi-objective local Q-learning and structural learning that alter the architecture of the memory structures by adding and removing nodes. The animat model has the following key properties: (1) autonomy: it operates in a fully automatic fashion, without any need for interaction with human engineers. In particular, it does not depend on human engineers to provide goals, tasks, or seed knowledge. Still, it can operate either with or without human interaction; (2) generality: it uses the same learning and decision-making mechanisms in all environments, e.g. desert environments and forest environments and for all animats, e.g. frog animats and bee animats; and (3) adequacy: it is able to learn basic forms of animal skills such as eating, drinking, locomotion, and navigation. Eight experiments are presented. The results obtained indicate that (i) dynamic memory structures are strictly more powerful than static; (ii) it is possible to use a fixed generic design to model basic cognitive processes of a wide range of animals and environments; and (iii) the animat framework enables a uniform and gradual approach to AGI, by successively taking on more challenging problems in the form of broader and more complex classes of environments