Rule-based evolutionary online learning systems, often referred to as Michigan-style learning classifier systems (LCSs), were proposed nearly thirty years ago (Holland, 1976; Holland, 1977) originally calling them cognitive systems. LCSs combine the strength of reinforcement learning with the generalization capabilities of genetic algorithms promising a flexible, online generalizing, solely reinforcement dependent learning system. However, despite several initial successful applications of LCSs and their interesting relations with animal learning and cognition, understanding of the systems remained somewhat obscured. Questions concerning learning complexity or convergence remained unanswered. Performance in different problem types, problem structures, concept spaces, and hypothesis spaces stayed nearly unpredictable. This thesis has the following three major objectives: (1) to establish a facetwise theory approach for LCSs that promotes system analysis, understanding, and design; (2) to analyze, evaluate, and enhance the XCS classifier system (Wilson, 1995) by the means of the facetwise approach establishing a fundamental XCS learning theory; (3) to identify both the major advantages of an LCS-based learning approach as well as the most promising potential application areas. Achieving these three objectives leads to a rigorous understanding

This paper explores a philosophy and connectionist algorithm for creating a long-term, self-motivated developmental robot control system. Self-motivation is viewed as an emergent property arising from two competing pressures: the need to accurately predict the environment while simultaneously wanting to seek out novelty in the environment. These competing internal pressures are designed to drive the system in a manner reminiscent of a co-evolutionary arms race. 1

Abstract. We introduce information-theoretic tools that can be used in an autonomous agent for constructing an internal predictive model based on event anticipation. This model relies on two different kinds of predictive relationships: time-delay relationships, where two events are related by a nearly constant time-delay between their occurrences; and contingency relationships, where proximity in time is the main property. We propose an anticipation architecture based on these tools that allows the construction of a relevant internal model of the environment through experience. Its design takes into account the problem of handling different time scales. We illustrate the effectiveness of the tools proposed with preliminary results about their ability to identify relevant relationships in different conditions. We describe how these principles can be embedded in a more complex architecture that allows action-decision according to reward expectation, and handling of more complex relationships. We conclude by discussing issues that were not addressed yet and some axis for future investigations. 1

Abstract not found

On behalf of:

Abstract. How can goals be represented in natural and artificial systems? How can they be learned? How can they trigger actions? This paper describes, analyses and compares two of the most influential models of goal-oriented behavior: the ideomotor principle (IMP), which was introduced in the psychological literature, and the “test, operate, test, exit ” model (TOTE) proposed in the field of cybernetic. This analysis indicates that the IMP and the TOTE highlight complementary aspects of goal-orientedness. In order to illustrate this point, the paper reviews three computational architectures that implement various aspects of the IMP and the TOTE, discusses their main peculiarities and limitations, and suggests how some of their features can be translated into specific mechanisms in order to implement them in artificial intelligent systems.

Abstract. Anticipation is one of the key aspects involved in flexible and adaptive behavior. The ability for an autonomous agent to extract a relevant model of its coupling with the environment and of the environment itself can provide it with a strong advantage for survival. In this work we develop an event-based anticipation framework for performing latent learning and we provide two mathematical tools to identify relevant relationships between events. These tools allow us to build a predictive model which is then embedded in an action-selection architecture to generate adaptive behavior. We first analyze some of the properties of the model in simple learning tasks. Its efficiency is evaluated in a more complex task where the agent has to adapt to a changing environment. In the last section we discuss extensions of the model presented. 1

Design and anticipation: towards an organisational view of design systems ISSN 1467-1298

Abstract. What does it mean for a system to be goal oriented? In this paper we investigate how goals are represented and how they activate actions. We review the main philosophical and psychological assumptions about the ideomotor principle and we compare it with the TOTE model in cybernetics. We also present three computational architectures that implement goal orientedness, discussing their main peculiarities and limitations with respect to the ideomotor principle and TOTE.

Abstract. The paper describes the design of an animat control system (the Animat Brain) that is based of the Petr K. Anokhin's theory of functional systems. We propose the animat control system that consists of a set of functional systems (FSs) and enables predictive and purposeful behavior. Each FS consists of two neural networks: the Actor and the Model. The Actors are intended to form chains of actions and the Models are intended to predict futures events. There are primary and secondary repertoires of behaviors: the primary repertoire is formed by evolution; the secondary repertoire is formed by means of learning. The paper describes both principles of the Animat Brain operation and the particular model of predictive behavior in cellular landmark environment. 1