Hierarchical Reinforcement Learning (HRL) enables autonomous decomposition of challenging long-horizon decision-making tasks into simpler subtasks. During the past years, the landscape of HRL research has grown profoundly, resulting in copious approaches. A comprehensive overview of this vast landscape is necessary to study HRL in an organized manner. We provide a survey of the diverse HRL approaches concerning the challenges of learning hierarchical policies, subtask discovery, transfer learning, and multi-agent learning using HRL. The survey is presented according to a novel taxonomy of the approaches. Based on the survey, a set of important open problems is proposed to motivate the future research in HRL. Furthermore, we outline a few suitable task domains for evaluating the HRL approaches and a few interesting examples of the practical applications of HRL in the Supplementary Material.

In their effort to measure yarn hairiness at high speed, the commercially available yarn hairiness testers resort to indirect techniques. Measurement of true length of all hairs can only be done by observing the yarn under a microscope and obtaining a trace of hairs. An attempt was made in this work to automate this task using digital image processing. The challenges were two-fold. The first was development of an algorithm capable of analysing yarn images taken under varying lighting conditions and varying yarn positions. The second was determination of minimum requirement of the image-capturing instrument. Both of these have been reported in this work. A new hairiness index has been proposed and suggested as a better indicator of hairiness than the traditional definition.

This paper describes aggregated learning models for Complex Word Identification (CWI) task in SemEval 2016. The work focused on selecting the features that determine complexity of words and used different combinations of support vector machine (SVM) and decision tree (DT) techniques for classification. These classifiers were pipelined with pre-processing and postprocessing blocks which helped improving accuracy of systems, though had little impact on recall. Four systems were evaluated on the test set; SVM and DT systems by team Bhasha achieved G score of 0.529 and 0.508 respectively and SVM&DT and SVMPP systems by team Garuda achieved G scores of 0.360 and 0.546 respectively.

This paper describes the polarity classification system designed for participation in SemEval-2016 Task 5 -ABSA. The aim is to determine the sentiment polarity expressed towards certain aspect within a consumer review. Our system is based on supervised learning using Support Vector Machine (SVM). We use standard features for basic classification model. On top this, we include rules to check precedent polarity sequence. This approach is experimental.

No abstract