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.

Fast Learning by Bounding Likelihoods in Sigmoid Type Belief Networks

Sigmoid type belief networks, a class of probabilistic neural networks, provide a natural framework for compactly representing probabilistic information in a variety of unsupervised and supervised learning problems. Often the parameters used in these networks need to be learned from examples. Unfortunately, estimating the parameters via exact probabilistic calculations (i.e, the EM-algorithm) is intractable even for networks with fairly small numbers of hidden units. We propose to avoid the infeasibility of the E step by bounding likelihoods instead of computing them exactly. We introduce extended and complementary representations for these networks and show that the estimation of the network parameters can be made fast (reduced to quadratic optimization) by performing the estimation in either of the alternative domains. The complementary networks can be used for continuous density estimation as well.

E-teaching vs e-learning : recursos educativos electrónicos para usar en el aula.

El artículo forma parte de una sección de la revista dedicada a innovación educativa

La adaptación al cambio de los Departamentos de Educación y Acción Cultural en la evolución de los museos : del simply watching al learn by doing.

Monográfico con el título: 'Patrimonio y Educación'. Resumen basado en el de la publicación

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.

Learning by Reading : A literature study on the use of authentic texts in the EFL upper elementary classroom

The English language is widely used throughout the world and has become a core subject in many countries, especially for students in the upper elementary classroom. While textbooks have been the preferred EFL teaching method for a long time, this belief has seemingly changed within the last few years. Therefore, this study looks at what prior research says about the use of authentic texts in the EFL upper elementary classroom with an aim to answer research questions on how teachers can work with authentic texts, what the potential benefits of using authentic texts are and what teachers and students say about the use of authentic texts in the EFL classroom. While this thesis is written from a Swedish perspective, it is recognized that many countries teach EFL. Therefore, international results have also been taken into consideration and seven previous research studies have been analyzed in order to gain a better understanding of the use of authentic texts in the EFL classroom. Results indicate that the use of authentic texts is beneficial in teaching EFL. However, many teachers are still reluctant to use these, mainly because of time constraints and the belief that such texts are too difficult for their students. Since these findings are mainly focused on areas outside of Sweden, additional research is needed before conclusions can be drawn on the use of authentic texts in the Swedish upper elementary EFL classroom.

Facilitation of learning in specialist nursing training in the PICU : the supervisors´ concerns in the learning situation

With the aim to unfold nurses’ concerns of the supervision of the student in the clinical caring situation of the vulnerable child, clinical nurses situated supervision of postgraduate nursing students in the Pediatric Intensive Care Unit (PICU) are explored. A qualitative approach, interpretive phenomenology, with participant observations and narrative interviews, was used. Two qualitative variations of patterns of meaning for the nurses’ clinical facilitation were disclosed in this study. Learning by doing theme supports the students learning by doing through performing skills and embracing routines. The reflecting theme supports thinking and awareness of the situation. As the supervisor often serves as a role model for the student this might have an immediate impact on how the student applies nursing care in the beginning of his or her career. If the clinical supervisor narrows the perspective and hinders room for learning the student will bring less knowledge from the clinical education than expected, which might result in reduced nursing quality.

Real Money, Real Lessons: In a course called learning by giving, students pursue and allot funding for area nonprofits

Students learn nonprofit ropes by seeking funding for area organizations.