Catálogo de publicaciones - libros

This paper investigates the processes used by an evolved, embodied simulated agent to adapt to large disruptive changes in its sensor morphology, whilst maintaining performance in a phototaxis task. By avoiding the imposition of separate mechanisms for the fast sensorimotor dynamics and the relatively slow adaptive processes, we are able to comment on the forms of adaptivity which emerge within our Evolutionary Robotics framework. This brings about interesting notions regarding the relationship between different timescales. We examine the dynamics of the network and find different reactive behaviours depending on the agent’s current sensor configuration, but are only able to begin to explain the dynamics of the transitions between these states with reference to variables which exist in the agent’s environment, as well as within its neural network ‘brain’.

The interaction of brain, body and environment can result in complex behavior with rich dynamics even for relatively simple agents. Such dynamics are, however, often notoriously difficult to analyze. In this paper we explore the case of a simple simulated robotic agent, equipped with a reactive neurocontroller and an energy level, that the agent has been evolved to re-charge. A dynamical systems analysis, shows that a non-neural internal state (energy level), despite its simplicity, dynamically modulates the agent-environment system’s behavioral attractors, such that the robot’s behavioral repertoire is continually adapted to its current situation and energy level.

Recent research in psychology and cognitive neuroscience are increasingly showing how emotion plays a crucial role in cognitive processes. Gradually, this knowledge is being used in Artificial Intelligence and Artificial Life areas in simulation and cognitive processes modeling. However, it lacks a theoretical framework that allows them to deal with emotion. In addiction, regarding emotion-based computational projects, controversial questions concerning the nature, function, and mechanisms of emotions, that must be considered, are mostly neglected on researches. The objective of this article is to discuss some of these problems and to present references that can be useful in their solution.

Adaptive responses to resource availability are common in natural systems. In this paper we explore one possible evolutionary cause of adaptive sleep/wake behavior. We subjected populations of digital organisms to an environment with a slowly diminishing resource and recorded their ability to adapt to the changing environment using sleep. We also quantified the selective pressure not to sleep in this competitive environment. We observed that diminishing resource availability can promote adaptive sleep responses in digital organisms even when there is an opportunity cost associated with sleeping.

Episodic memory represents personal history of an entity. Human-like agents with are able to reconstruct their personal stories to a large extent. Since these agents typically live in dynamic environments that change beyond their capabilities, their memory must cope with determining trustfulness of memory records. In this paper, we propose an associative network addressing this issue with regard to records about objects an agent met during its live. The network is presently being implemented into our case-study human-like agent with a full episodic memory.

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.

While looking at aging of individuals, we take for granted that one of aging reasons is related with individual’s ability to learn rapidly, to adapt to sudden environmental changes and survive. We explain maturation and aging of standard non-linear single layer perceptron by increasing of components of the weight vector and dramatic decline of a gradient. We analyze also artificial immune system trained by the mutation based genetic learning algorithm. In both, the connectionist and genetic learning, we obtain saturation and an inverted letter “U” shape dependence between success in learning and the “age”.

This paper examines the effects of lifetime learning on the diversity and fitness of a population. Our experiments measure the phenotypic diversity of populations evolving by purely genetic means (population learning) and of others employing both population learning and lifetime learning. The results obtained show, as in previous work, that the addition of lifetime learning results in higher levels of fitness than population learning alone. More significantly, results from the diversity measure show that lifetime learning is capable of sustaining higher levels of diversity than population learning alone.

One advantage of the asynchronous and distributed character of embodied evolution is that it can be executed on real robots without external supervision. Further, evolutionary progress can be measured in real time instead of in generation based evaluation cycles. By combining embodied evolution with lifetime learning, we investigated a largely neglected aspect with respect to the common assumption that learning can guide evolution, the influence of maturation time during which an individual can develop its behavioral skills. Even though we found only minor differences between the evolution with and without learning, our results, derived from competitive evolution in predator-prey systems, demonstrate that the right timing of maturation is crucial for the progress of evolutionary success. Our findings imply that the time of maturation has to be considered more seriously as an important factor to build up empirical evidence for the hypothesis that learning facilitates evolution.

Studying the role played by evolution and learning in adaptive behavior is a very important topic in artificial life research. This paper investigates the interplay between learning and evolution when agents have to solve several different tasks, as it is the case for real organisms but typically not for artificial agents. Recently, an important thread of research in machine learning and developmental robotics has begun to investigate how agents can solve different tasks by composing general skills acquired on the basis of internal motivations. This work presents a hierarchical, neural-network, actor-critic architecture designed for implementing this kind of intrinsically motivated reinforcement learning in real robots. We compare the results of several experiments in which the various components of the architecture are either trained during lifetime or evolved through a genetic algorithm. The most important results show that systems using both evolution and learning outperform systems using either one of the two, and that, among the former, systems evolving internal reinforcers for learning building-block skills have a higher evolvability than those directly evolving the related behaviors.