Reinforcement Learning by Policy Search

One objective of artificial intelligence is to model the behavior of an intelligent agent interacting with its environment. The environment's transformations can be modeled as a Markov chain, whose state is partially observable to the agent and affected by its actions; such processes are known as partially observable Markov decision processes (POMDPs). While the environment's dynamics are assumed to obey certain rules, the agent does not know them and must learn. In this dissertation we focus on the agent's adaptation as captured by the reinforcement learning framework. This means learning a policy---a mapping of observations into actions---based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with the environment. The set of policies is constrained by the architecture of the agent's controller. POMDPs require a controller to have a memory. We investigate controllers with memory, including controllers with external memory, finite state controllers and distributed controllers for multi-agent systems. For these various controllers we work out the details of the algorithms which learn by ascending the gradient of expected cumulative reinforcement. Building on statistical learning theory and experiment design theory, a policy evaluation algorithm is developed for the case of experience re-use. We address the question of sufficient experience for uniform convergence of policy evaluation and obtain sample complexity bounds for various estimators. Finally, we demonstrate the performance of the proposed algorithms on several domains, the most complex of which is simulated adaptive packet routing in a telecommunication network.

Using zappers in Common Learning Spaces (Windows XP)

This resource is now obsolete and has been replaced by http://www.edshare.soton.ac.uk/5920/ This PowerPoint is an animated step-by-step guide that shows tutors how to use zappers in a teaching session. It covers starting the PC, distributing the zappers, plugging in the receiver, starting the software, running the presentation and managing voting, saving data at the end and collecting the handsets. It takes around 5 minutes to view.

INFO2009 Professional Bodies in the workplace

Links to BCS Code of Conduct and Royal Academy of Engineering Ethical Principles are used in classroom activity. BCS code of good practice also linked. Also archive from A/y 2009-10. See also shares 6232 and 4009

Educational/training situated e-learning

A small selection of the range of educational/training situated e-learning in Southampton Education School

The biofeedback use in motor learning of people with spinal cord injury

The use of biofeedback in the spinal cord injuryperson rehabilitation has been increasing eventhough there are no data about the effi cacy of suchtechnique. The study aimed to evaluate the effi cacyof the technique in the motor rehabilitation ofspinal cord injured patients with different lesions.Using case studies, three participants, two paraplegicsand one quadriplegic, with different lesionlevels and degrees of defi ciency were exposed toelectromyography biofeedback training sessions.Data were obtained from the training sessions withbiofeedback, from three manual test examinationsof the muscles straight and from the reports of theparticipants after the training process. These sourcesof data were compared and the results of all thethree different sources showed improvement forall the participants. The study concluded that theelectromyography biofeedback technique can bean important tool in the rehabilitation process ofpatients with this kind of lesion.

A new concept for museum training in Germany

To talk about a new concept for museum training seems perhaps, to be a little bit exaggerated. For long time you have all been talking about concepts and contents for museum training and as I figured out the debate on the topic in Germany is as old as the appearance of national museums in the 19th century. Men like Theodor Mommsen, Rudolph Virchow, Alfred Lichtwark, all well known historians and supporters of the museum idea, spoke and wrote not only about the importance of museums as cultural and educational institutions but also supported the idea of professionalisation of museums work. Some of the ideas of our ancestors are still part of an ongoing discussion. The topic of my talk today will be what king of personnel a museum of our time needs to cope with the growing demand for internal and external organization. I shall present to you a new training program for museum workers in Germany which aims not to produce a new group of researchers but to prepare students for the practical work in the museum field.

Case study: acquisition of Japanese in aural language by the four year old child whose hearing loss was detected when he was visiting in U. S. with his family

Access to thesis is restricted. Contact Archives and Rare Books. This paper reports the results of language training for a newly diagnosed hearing impaired Japanese child using methods from the CID parent-infant program.

Cambio climático y mundo en desarrollo: las insidias del learning by doing… (Otros Temas)

No hay duda, el mundo parece estar de acuerdo en que la reunión de Copenhague, el pasado mes de diciembre, fue un fracaso rotundo. Hay quienes no rescatan nada de la cumbre, sencillamente todo acabó en una operación de fachada de última hora, en la que un puñado de países, en nombre de todos los demás y para sacar la cara frente al mundo, presentaba el famoso Acuerdo de Copenhague.

Rapid word learning by 15-month-olds under tightly-controlled conditions

Infants (12 to 17 months) were taught 2 novel words for 2 images of novel objects, by pairing isolated auditory labels with to-be-associated images. Comprehension was tested using a preferential looking task in which the infant was presented with both images together with an isolated auditory label. The auditory label usually, but not always, matched one of the images. Infants looked preferentially at images that matched the auditory stimulus. The experiment controlled within-subjects for both side bias and preference for previously named items. Infants showed learning after 12 presentations of the new words. Evidence is presented that, in certain circumstances, the duration of longest look at a target may be a more robust measure of target preference than overall looking time. The experiment provides support for previous demonstrations of rapid word learning by pre-vocabulary spurt children, and offers some methodological improvements to the preferential looking task.

From activity to active learning: drawing and dialogue interaction in virtual learning environments for computer-supported collaborative work in design.

Virtual learning environments (VLEs) would appear to be particular effective in computer-supported collaborative work (CSCW) for active learning. Most research studies looking at computer-supported collaborative design have focused on either synchronous or asynchronous modes of communication, but near-synchronous working has received relatively little attention. Yet it could be argued that near-synchronous communication encourages creative, rhetorical and critical exchanges of ideas, building on each other’s contributions. Furthermore, although many researchers have carried out studies on collaborative design protocol, argumentation and constructive interaction, little is known about the interaction between drawing and dialogue in near-synchronous collaborative design. The paper reports the first stage of an investigation into the requirements for the design and development of interactive systems to support the learning of collaborative design activities. The aim of the study is to understand the collaborative design processes while sketching in a shared white board and audio conferencing media. Empirical data on design processes have been obtained from observation of seven sessions with groups of design students solving an interior space-planning problem of a lounge-diner in a virtual learning environment, Lyceum, an in-house software developed by the Open University to support its students in collaborative learning.

Improving educational functions in botanic gardens by employing landscape narratives

Landscape narrative, combining landscape and narrative, has been employed to create storytelling layouts and interpretive information in some famous botanic gardens. In order to assess the educational effectiveness of using "landscape narrative" in landscape design, the Heng-Chun Tropical Botanical Garden in Taiwan was chosen as research target for an empirical study. Based on cognitive theory and the affective responses of environmental psychology, computer simulations and video recordings were used to create five themed display areas with landscape narrative elements. Two groups of pupils watched simulated films. The pupils were then given an evaluation test and questionnaire, to determine the effectiveness of the landscape narrative. When the content was well associated and matched with the narrative landscape, the comprehension and retention of content was increased significantly. The results also indicated that visual preference of narrative landscape scenes was increased. This empirical study can be regarded as a successful model of integrating landscape narrative and interpretation practice that can be applied to the design of new theme displays in botanic gardens to improve both the effectiveness of interpretation plans and the visual preference of visitors. (c) 2008 Elsevier B.V. All rights reserved.

Recalled relationships with parents and perceptions of professional support in mothers of infants treated for cleft lip

This study examined whether individual differences in perception of the quality of professional support available at a time of stress may be associated with security of attachment. We developed a new measure of parents' perceptions of emotional and practical support provided by a wide range of professionals involved in the treatment of infants with cleft lip. it showed good internal reliability and stability over 4 months. Mothers of 102 infants with cleft lip, with or without cleft palate, completed the measure at 2 and 6 months, together with the Parental Bonding Instrument and the General Health Questionnaire. Mean scores reflecting how much they could trust or talk frankly, or share their worst fears, with professionals, and the extent to which they saw them as a source of useful information or practical help, were lower among mothers with recollections of low maternal care in childhood, or high control. This was the case at 2 and 6 months, and there were some indications of an increasing contribution of low maternal care from 2 to 6 months. The associations were not explained by current depression. Further research is needed to clarify the role of attachment processes in parents' responses to serious medical conditions in their children, and into the implications for the way professionals in paediatric services provide support.

Once upon a time, there was a pulchritudinous princess…: the role of word definitions and multiple story contexts in children’s learning of difficult vocabulary

The close relationship between children’s vocabulary size and their later academic success has led researchers to explore how vocabulary development might be promoted during the early school years. We describe a study that explored the effectiveness of naturalistic classroom storytelling as an instrument for teaching new vocabulary to six- to nine-year-old children. We examined whether learning was facilitated by encountering new words in single versus multiple story contexts, or by the provision of age-appropriate definitions of words as they were encountered. Results showed that encountering words in stories on three occasions led to significant gains in word knowledge in children of all ages and abilities, and that learning was further enhanced across the board when teachers elaborated on the new words’ meanings by providing dictionary definitions. Our findings clarify how classroom storytelling activities can be a highly effective means of promoting vocabulary development.