Buch, Englisch, 458 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 8218 g
ISBN: 978-3-642-32374-4
Verlag: Springer
It has become clear to researchers in robotics that current approaches are yielding systems with limited autonomy and capacity for self-improvement. To learn autonomously and in a cumulative fashion is one of the hallmarks of intelligence, and we know that higher mammals engage in exploratory activities with the environment that are not directed to pursue goals of immediate relevance for the survival and reproduction of the organism but are instead driven by intrinsic motivations such as curiosity, interest in novel stimuli or surprising events, and inter¬est in learning new behaviours. The adaptive value of such intrinsically motivated activities lies in the fact that they allow the cumulative acquisition of knowledge and skills that can be later used to accomplish fitness-enhanc¬ing goals. Intrinsic motivations continue during adulthood, and in humans they underlie lifelong learning, artistic creativity, and scientific discovery, while they are also the basis for processes that strongly affect human wellbeing, such as the sense of competence, self-determination, and self-esteem.
This book has two aims: to present state-of-the-art research on intrinsically motivated learning, and to identify the related scientific and technological open challenges and research directions. After explaining the concept of intrinsic motivations, the book introduces a taxonomy of three classes of intrinsic-motivation mechanisms: those based on predictors, on novelty detection, and on competence. The remaining chapters are organized into six parts: the chapters in Part I give general overviews on the concept of intrinsic motivations, their function, and possible mechanisms for implementing them; Parts II, III, and IV focus on the three above-mentioned classes of intrinsic-motivation mechanisms; Part V discusses mechanisms that are complementary to intrinsic motivations; and Part VI introduces tools and experimental frameworks for investigating intrinsic motivations.
The contributing authors are among the pioneers carrying out fundamental work on this topic, drawn from related disciplines such as artificial intelligence, robotics, artificial life, evolution, machine learning, developmental psychology, cognitive science, and neuroscience. The book will be of value to graduate students and academic researchers in these domains, and to engineers engaged with the design of autonomous, adaptive robotics.
Zielgruppe
Research
Autoren/Hrsg.
Fachgebiete
- Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
- Sozialwissenschaften Psychologie Allgemeine Psychologie Kognitionspsychologie Emotion, Motivation, Handlung
- Sozialwissenschaften Psychologie Allgemeine Psychologie Kognitionspsychologie Lernen
- Naturwissenschaften Biowissenschaften Biowissenschaften Evolutionsbiologie
- Interdisziplinäres Wissenschaften Wissenschaften Interdisziplinär Neurowissenschaften, Kognitionswissenschaft
- Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik Robotik
Weitere Infos & Material
Chap. 1 - Intrinsically Motivated Learning Systems: An Overview.- Chap. 2 - Intrinsic Motivation and Reinforcement Learning.- Chap. 3 - Functions and Mechanisms of Intrinsic Motivations.- Chap. 4 - Exploration from Generalization Mediated by Multiple Controllers.- Chap. 5 - Maximizing Fun by Creating Data with Easily Reducible Subjective Complexity.- Chap. 6 - The Role of the Basal Ganglia in Discovering Novel Actions.- Chap. 7 - Action Discovery and Intrinsic Motivation: A Biologically Constrained Formalisation.- Chap 8 - Novelty Detection as an Intrinsic Motivation for Cumulative Learning Robots.- Chap. 9 - Novelty and Beyond: Towards Combined Motivation Models and Integrated Learning Architectures.- Chap. 10 - The Hippocampal-VTA Loop: The Role of Novelty and Motivation in Controlling the Entry of Information into Long-Term Memory.- Chap. 11 - Deciding Which Skill to Learn When: Temporal-Di erence Competence-Based Intrinsic Motivation (TD-CB-IM).- Chap. 12 - Intrinsically Motivated Affordance Discovery and Modeling.- Chap. 13 - Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints.- Chap. 14 - Investigating the Origins of Intrinsic Motivation in Human Infants.- Chap. 15 - A Novel Behavioural Task for Researching Intrinsic Motivations.- Chap. 16 - The Mechatronic Board : A Tool to Study Intrinsic Motivations in Humans, Monkeys, and Humanoid Robots.- Chap. 17 - The iCub Platform: A Tool for Studying Intrinsically Motivated Learning.