Results 1 - 10
of
43
A Computational Theory of Executive Cognitive Processes and Multiple-Task Performance: Part 2. . .
- PSYCHOLOGICAL REVIEW
, 1997
"... ..."
Intrinsic motivation systems for autonomous mental development
- IEEE Transactions on Evolutionary Computation
, 2007
"... Abstract—Exploratory activities seem to be intrinsically rewarding for children and crucial for their cognitive development. Can a machine be endowed with such an intrinsic motivation system? This is the question we study in this paper, presenting a number of computational systems that try to captur ..."
Abstract
-
Cited by 81 (25 self)
- Add to MetaCart
Abstract—Exploratory activities seem to be intrinsically rewarding for children and crucial for their cognitive development. Can a machine be endowed with such an intrinsic motivation system? This is the question we study in this paper, presenting a number of computational systems that try to capture this drive towards novel or curious situations. After discussing related research coming from developmental psychology, neuroscience, developmental robotics, and active learning, this paper presents the mechanism of Intelligent Adaptive Curiosity, an intrinsic motivation system which pushes a robot towards situations in which it maximizes its learning progress. This drive makes the robot focus on situations which are neither too predictable nor too unpredictable, thus permitting autonomous mental development. The complexity of the robot’s activities autonomously increases and complex developmental sequences self-organize without
Evolving Internal Reinforcers for an Intrinsically Motivated Reinforcement-Learning Robot
- 6TH IEEE INTERNATIONAL CONFERENCE ON DEVELOPMENT AND LEARNING (ICDL2007) (SUBMITTED
"... ... (IMRL) has been proposed as a framework within which agents exploit “internal reinforcement” to acquire general-purpose building-block behaviors (“skills”) which can be later combined for solving several specific tasks. The architectures so far proposed within this framework are limited in that: ..."
Abstract
-
Cited by 15 (2 self)
- Add to MetaCart
... (IMRL) has been proposed as a framework within which agents exploit “internal reinforcement” to acquire general-purpose building-block behaviors (“skills”) which can be later combined for solving several specific tasks. The architectures so far proposed within this framework are limited in that: (1) they use hardwired “salient events” to form and train skills, and this limits agents’ autonomy; (2) they are applicable only to problems with abstract states and actions, as grid-world problems. This paper proposes solutions to these problems in the form of a hierarchical reinforcement-learning architecture that: (1) exploits Evolutionary Robotics techniques so to allow the system to autonomously discover “salient events”; (2) uses neural networks so to allow the system to cope with continuous states and noisy environments. The viability of the proposed approach is demonstrated with a simulated robotic scenario.
Evolution and Learning in an Intrinsically Motivated Reinforcement Learning Robot
- PROCEEDINGS OF THE 9 TH EUROPEAN CONFERENCE ON ARTIFICIAL LIFE. IN
"... 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 no ..."
Abstract
-
Cited by 10 (2 self)
- Add to MetaCart
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.
About a Framework for Information and Information Processing of Learning Systems
"... Information and information processing are one of the most important aspects of dynamic systems. The term 'information', that is used in various contexts, might better be replaced with one that incorporates novelty, activity and learning. Many important communications of learning systems are non-erg ..."
Abstract
-
Cited by 9 (5 self)
- Add to MetaCart
Information and information processing are one of the most important aspects of dynamic systems. The term 'information', that is used in various contexts, might better be replaced with one that incorporates novelty, activity and learning. Many important communications of learning systems are non-ergodic. The ergodicity assumption in Shannon's communication theory restricts his and all related concepts to systems that can not learn. For learning systems that interact with their environments, the more primitive concept of 'variety' will have to be used, instead of probability. Humans have a fundamental need for variety: he can't permanently perceive the same context, he can't do always the same things. The fundamental need for variety leads to a different interpretation of human behaviour that is often classified as "errors". Variety is the basis to measure complexity. Complexity in the relationship between a learning system and his context can be expressed as incongruity. Incongruity is...
Behavior Analysis and Decision Making
, 1998
"... This paper reports on the application of behavior-analytic methodology and orientation to some important phenomena in decision making that have perhaps received insufficient attention from behavior analysts. ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
This paper reports on the application of behavior-analytic methodology and orientation to some important phenomena in decision making that have perhaps received insufficient attention from behavior analysts.
Aesthetics as a key dimension for designing ubiquitous entertainment systems
- The 2nd International Workshop on Ubiquitous Home—ubiquitous society and entertainment. (pp. 85-94) NICT Keihanna and Kyoto
, 2005
"... Abstract. In this paper we review the current understanding of aesthetics. There are three aspects to aesthetics namely: the form, the action and the experience. We explore these aspects and highlight their relevance for entertainment. We then investigate ubiquitous entertainment systems notably fro ..."
Abstract
-
Cited by 6 (4 self)
- Add to MetaCart
Abstract. In this paper we review the current understanding of aesthetics. There are three aspects to aesthetics namely: the form, the action and the experience. We explore these aspects and highlight their relevance for entertainment. We then investigate ubiquitous entertainment systems notably from an interaction point of view. We advocate and define how ubiquitous entertainment could and should rely on aesthetics as a framework for the delivery of usable systems. 1
Scaffolding deep comprehension strategies through Point&Query, AutoTutor, and iSTART
- Educational Psychologist
, 2005
"... It is well-documented that most students do not have adequate proficiencies in inquiry and metacognition, particularly at deeper levels of comprehension that require explanatory reasoning. The proficiencies are not routinely provided by teachers and normal tutors so it is worthwhile to turn to compu ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
It is well-documented that most students do not have adequate proficiencies in inquiry and metacognition, particularly at deeper levels of comprehension that require explanatory reasoning. The proficiencies are not routinely provided by teachers and normal tutors so it is worthwhile to turn to computer-based learning environments. This article describes some of our recent computer systems that were designed to facilitate explanation-centered learning through strategies of inquiry and metacognition while students learn science and technology content. Point&Query augments hypertext, hypermedia, and other learning environments with question–answer facilities that are under the learner control. AutoTutor and iSTART use animated conversational agents to scaffold strategies of inquiry, metacognition, and explanation construction. AutoTutor coaches students in generating answers to questions that require explanations (e.g., why, what-if, how) by holding a mixed-initiative dialogue in natural language. iSTART models and coaches students in constructing self-explanations and in applying other metacomprehension strategies while reading text. These systems have shown promising results in tests of learning gains and learning strategies. Imagine an active, curious, self-regulated learner who asks
The Process of Organizational Communication: A Model and Field Study
, 2000
"... Research in computer-mediated communication has usually emphasized the cognitive over the social aspects of communication, the medium over the message, and the product of communication over the process. In contrast, this paper emphasizes three constructs of the communication process: goal-based comm ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
Research in computer-mediated communication has usually emphasized the cognitive over the social aspects of communication, the medium over the message, and the product of communication over the process. In contrast, this paper emphasizes three constructs of the communication process: goal-based communication strategies, message form, and medium. We seek to balance cognitive and social communication strategies and to combine new and old measures of the message form (organization, formality, and size). A field study in an academic institution examines the content of text-based communication delivered by letter, memo, fax, and email. As expected, people prefer certain message and medium attributes for certain strategies. These findings are further investigated using open-ended interviews. We conclude with examples of practical implications on designing and implementing computer-mediated communication. Index Terms---Communication strategies, computer-mediated communication, media richness ...
Learning From Experience in High-Hazard Organizations.” http://ocw.mit.edu/NR/rdonlyres/Aeronautics-and-Astronautics/16358JSpring-2005/09BD2DD3-A2FE-4589-99A7-4EE545C1689D/0/carroll1.pdf
- Organizational Learning Activities in High-Hazard Industries: The Logics Underlying Self-Analysis.” Journal of Management Studies. 35:6
, 1998
"... Learning from experience, the cyclical interplay of thinking and doing, is increasingly important as organizations struggle to cope with rapidly changing environments and more complex and interdependent sets of knowledge. This paper confronts two central issues for organizational learning: (1) how i ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
Learning from experience, the cyclical interplay of thinking and doing, is increasingly important as organizations struggle to cope with rapidly changing environments and more complex and interdependent sets of knowledge. This paper confronts two central issues for organizational learning: (1) how is local learning (by individuals or small groups) integrated into collective learning by organizations? and (2) what are the differences between learning practices that focus on control, elimination of surprises, and single-loop incremental “fixing ” of problems with those that focus on deep or radical learning, double-loop challenging of assumptions, and discovery of new opportunities? We articulate these relationships through an analysis of learning practices in high-hazard organizations, specifically, problem investigation teams that examine the most serious and troubling events and trends in nuclear power plants and chemical plants. Our analysis suggests a four-stage model of organizational learning reflecting different approaches to control and learning. LEARNING FROM EXPERIENCE IN HIGH-HAZARD ORGANIZATIONS 1

