An ambitious goal of transfer learning is to learn a task faster after training on a different, but related, task. In this paper we extend a previously successful temporal difference (Sutton & Barto, 1998) approach to transfer in reinforcement learning (Sutton & Barto, 1998) tasks to work with policy search. In particular, we show how to construct a mapping to translate a population of policies...

An ambitious goal of transfer learning is to learn a task faster after training on a different, but related, task. In this paper we extend a previously successful temporal difference (Sutton & Barto, 1998) approach to transfer in reinforcement learning (Sutton & Barto, 1998) tasks to work with policy search. In particular, we show how to construct a mapping to translate a population of policies...

Switching between tasks that overlap in perceptual and response characteristics is assumed to rely upon the maintenance of task representations in prefrontal cortex (PFC). However, task-switching studies demonstrate ‘‘switch costs,’’ even when there is sufficient time to prepare for a new task. These costs suggest that task-switching performance reflects a complex interplay between priming and ...

Tree structures are a natural way of describing occurrence relationships between attributes in a dataset. We define a new class of tree patterns for unordered 0–1 data and consider the problem of discovering frequently occurring members of this pattern class. Intuitively, a tree T occurs in a row u of the data, if the attributes of T that occur in u form a subtree of T containing the root. We s...

A number of recent publications have made use of the incremental output of stochastic parsers to derive measures of high utility for psycholinguistic modeling, following the work of Hale (2001; 2003; 2006). In this paper, we present novel methods for calculating separate lexical and syntactic surprisal measures from a single incremental parser using a lexicalized PCFG. We also present an approx...

Academics today are working in a time of intense pressure research publishing, with greater expectations, more explicit incentives and fiercer competition than ever before. In this paper we explore whether has led authors to rhetorically ‘sell’ or ‘hype’ their studies. Based on corpus 360 articles leading journals four disciplines at three periods over the past 50 years, trace use 400 ‘hyping’ ...

Some researchers demonstrate that there is a positive relationship between competition and innovation; however, others depict that it is negative. Two contradictory results exist at the same time. Moreover, there are studies which show that the relationship is nonlinear. This study is to explore this relationship by examining the empirical data in Taiwan. We use Curve Estimation and Logistic Re...