Infinite-horizon policy-gradient estimation

Gradient-based approaches to direct policy search in reinforcement learning have received much recent attention as a means to solve problems of partial observability and to avoid some of the problems associated with policy degradation in value-function methods. In this paper we introduce GPOMDP, a simulation-based algorithm for generating a biased estimate of the gradient of the average reward in Partially Observable Markov Decision Processes (POMDPs) controlled by parameterized stochastic policies. A similar algorithm was proposed by Kimura, Yamamura, and Kobayashi (1995). The algorithm's chief advantages are that it requires storage of only twice the number of policy parameters, uses one free parameter β ∈ [0,1) (which has a natural interpretation in terms of bias-variance trade-off), and requires no knowledge of the underlying state. We prove convergence of GPOMDP, and show how the correct choice of the parameter β is related to the mixing time of the controlled POMDP. We briefly describe extensions of GPOMDP to controlled Markov chains, continuous state, observation and control spaces, multiple-agents, higher-order derivatives, and a version for training stochastic policies with internal states. In a companion paper (Baxter, Bartlett, & Weaver, 2001) we show how the gradient estimates generated by GPOMDP can be used in both a traditional stochastic gradient algorithm and a conjugate-gradient procedure to find local optima of the average reward. ©2001 AI Access Foundation and Morgan Kaufmann Publishers. All rights reserved.

Teachers' and education students' perceptions of and reactions to children with and without the diagnostic label 'ADHD'

Thirty-four elementary school teachers and 32 education students from Canada rated their reactions towards vignettes describing children who met attention-deficit/hyperactivity disorder (ADHD) symptom criteria that included or did not include the label “ADHD.” “ADHD”-labeled vignettes elicited greater perceptions of the child's impairment as well as more negative emotions and less confidence in the participants, although it also increased participants' willingness to implement treatment interventions. Ratings were similar to vignettes of boys versus girls; however, important differences in ratings between teachers and education students emerged and are discussed. Finally, we investigated the degree to which teachers' professional backgrounds influenced bias based on the label “ADHD.” Training specific to ADHD consistently predicted label bias, whereas teachers' experience working with children with ADHD did not.

Health Librarianship Workforce and Education : Research to plan the future. Final Report.

In late 2009, Health Libraries Australia (HLA) received a small grant to undertake a national research project to determine the future requirements for health librarians in the workforce in Australia and develop a structured, modular education framework (post-graduate qualification and continuing professional development structure) to meet these requirements. The main objective was to consider the education and professional development framework that would ensure that health librarians have a clearly defined scope of practice and the specific competency based knowledge and skills that enable them to contribute to the design and delivery of high quality health services in this country. The final report presents a detailed discussion of the changing Australian healthcare environment and the resulting impact on the health library sector, as well as an overview of international trends in health libraries and the implications for Australian health librarianship education. The research methodology is outlined, followed by an analysis of the findings from the two surveys with health librarians and health library managers and the semi-structured interviews conducted with employers. The Medical Library Association (MLA) in the United States had developed a policy document detailing the competencies required by health librarians. It was found that the MLA competencies represented an accepted professional framework of skills which could be used objectively in the survey instrument to measure the areas of professional knowledge and responsibilities that were relevant in the current workplace, and to identify how these requirements might change in the next three to five years. The research results underscore the imperative for health librarians to engage in regular, relevant professional development activities that will enable them to stay abreast with the rapid contextual changes impacting on their practice. In order to be accepted as key members of the multi-disciplinary health professional team, it is strongly believed that health librarians should commit to establishing the mechanisms for specialist certification maintained through compulsory CPD in an ongoing three-year cycle of revalidation. This development would align ALIA and health librarians with other health sector professional associations which are responsible for the self regulation of entry to and continuation in their profession.

The influence of personality traits in predicting information processing and message persuasiveness

Gray‘s (2000) revised Reinforcement Sensitivity Theory (r-RST) was used to investigate personality effects on information processing biases to gain-framed and loss-framed anti-speeding messages and the persuasiveness of these messages. The r-RST postulates that behaviour is regulated by two major motivational systems: reward system or punishment system. It was hypothesised that both message processing and persuasiveness would be dependent upon an individual‘s sensitivity to reward or punishment. Student drivers (N = 133) were randomly assigned to view one of four anti-speeding messages or no message (control group). Individual processing differences were then measured using a lexical decision task, prior to participants completing a personality and persuasion questionnaire. Results indicated that participants who were more sensitive to reward showed a marginally significant (p = .050) tendency to report higher intentions to comply with the social gain-framed message and demonstrate a cognitive processing bias towards this message, than those with lower reward sensitivity.