scholarly journals Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences

2021 ◽  
pp. 027836492110416
Author(s):  
Erdem Bıyık ◽  
Dylan P. Losey ◽  
Malayandi Palan ◽  
Nicholas C. Landolfi ◽  
Gleb Shevchuk ◽  
...  
Keyword(s):  
Data Sources ◽  
Mobile Manipulator ◽  
Sources Of Information ◽  
Multiple Sources ◽  
Reward Function ◽  
Multiple Data ◽  
Preference Queries ◽  
Passive Data ◽  
Reward Functions ◽  
Human Teachers

Reward functions are a common way to specify the objective of a robot. As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers. Importantly, data from human teachers can be collected either passively or actively in a variety of forms: passive data sources include demonstrations (e.g., kinesthetic guidance), whereas preferences (e.g., comparative rankings) are actively elicited. Prior research has independently applied reward learning to these different data sources. However, there exist many domains where multiple sources are complementary and expressive. Motivated by this general problem, we present a framework to integrate multiple sources of information, which are either passively or actively collected from human users. In particular, we present an algorithm that first utilizes user demonstrations to initialize a belief about the reward function, and then actively probes the user with preference queries to zero-in on their true reward. This algorithm not only enables us combine multiple data sources, but it also informs the robot when it should leverage each type of information. Further, our approach accounts for the human’s ability to provide data: yielding user-friendly preference queries which are also theoretically optimal. Our extensive simulated experiments and user studies on a Fetch mobile manipulator demonstrate the superiority and the usability of our integrated framework.

scholarly journals Big data integration enhancement based on attributes conditional dependency and similarity index method

2021 ◽  
Vol 18 (6) ◽  
pp. 8661-8682
Author(s):  
Vishnu Vandana Kolisetty ◽  
◽  
Dharmendra Singh Rajput ◽  
Keyword(s):  
Big Data ◽  
Semantic Analysis ◽  
Similarity Index ◽  
Data Sources ◽  
Sources Of Information ◽  
Index Method ◽  
Related Information ◽  
Multiple Data ◽  
Integration Techniques ◽  
Conditional Dependency

<abstract> <p>Big data has attracted a lot of attention in many domain sectors. The volume of data-generating today in every domain in form of digital is enormous and same time acquiring such information for various analyses and decisions is growing in every field. So, it is significant to integrate the related information based on their similarity. But the existing integration techniques are usually having processing and time complexity and even having constraints in interconnecting multiple data sources. Many of these sources of information come from a variety of sources. Due to the complex distribution of many different data sources, it is difficult to determine the relationship between the data, and it is difficult to study the same data structures for integration to effectively access or retrieve data to meet the needs of different data analysis. In this paper, proposed an integration of big data with computation of attribute conditional dependency (ACD) and similarity index (SI) methods termed as ACD-SI. The ACD-SI mechanism allows using of an improved Bayesian mechanism to analyze the distribution of attributes in a document in the form of dependence on possible attributes. It also uses attribute conversion and selection mechanisms for mapping and grouping data for integration and uses methods such as LSA (latent semantic analysis) to analyze the content of data attributes to extract relevant and accurate data. It performs a series of experiments to measure the overall purity and normalization of the data integrity, using a large dataset of bibliographic data from various publications. The obtained purity and NMI ratio confined the clustered data relevancy and the measure of precision, recall, and accurate rate justified the improvement of the proposal is compared to the existing approaches.</p> </abstract>

scholarly journals Extending density surface models to include multiple and double-observer survey data

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e12113
Author(s):  
David L. Miller ◽  
David Fifield ◽  
Ewan Wakefield ◽  
Douglas B. Sigourney
Keyword(s):  
Spatial Model ◽  
Distance Sampling ◽  
Additive Model ◽  
Data Sources ◽  
Multiple Sources ◽  
Multiple Data Sources ◽  
Multiple Data ◽  
Surface Models ◽  
Density Surface ◽  
Double Observer

Spatial models of density and abundance are widely used in both ecological research (e.g., to study habitat use) and wildlife management (e.g., for population monitoring and environmental impact assessment). Increasingly, modellers are tasked with integrating data from multiple sources, collected via different observation processes. Distance sampling is an efficient and widely used survey and analysis technique. Within this framework, observation processes are modelled via detection functions. We seek to take multiple data sources and fit them in a single spatial model. Density surface models (DSMs) are a two-stage approach: first accounting for detectability via distance sampling methods, then modelling distribution via a generalized additive model. However, current software and theory does not address the issue of multiple data sources. We extend the DSM approach to accommodate data from multiple surveys, collected via conventional distance sampling, double-observer distance sampling (used to account for incomplete detection at zero distance) and strip transects. Variance propagation ensures that uncertainty is correctly accounted for in final estimates of abundance. Methods described here are implemented in the dsm R package. We briefly analyse two datasets to illustrate these new developments. Our new methodology enables data from multiple distance sampling surveys of different types to be treated in a single spatial model, enabling more robust abundance estimation, potentially over wider geographical or temporal domains.

scholarly journals A hands-on introduction to querying evolutionary relationships across multiple data sources using SPARQL

F1000Research ◽  
2019 ◽  
Vol 8 ◽  
pp. 1822 ◽  
Author(s):  
Ana Claudia Sima ◽  
Christophe Dessimoz ◽  
Kurt Stockinger ◽  
Monique Zahn-Zabal ◽  
Tarcisio Mendes de Farias
Keyword(s):  
Query Language ◽  
Data Sources ◽  
Multiple Sources ◽  
Semantic Web Technologies ◽  
Genome Database ◽  
Web Technologies ◽  
Multiple Data ◽  
Hands On ◽  
Description Framework ◽  
Different Sources

The increasing use of Semantic Web technologies in the life sciences, in particular the use of the Resource Description Framework (RDF) and the RDF query language SPARQL, opens the path for novel integrative analyses, combining information from multiple sources. However, analyzing evolutionary data in RDF is not trivial, due to the steep learning curve required to understand both the data models adopted by different RDF data sources, as well as the SPARQL query language. In this article, we provide a hands-on introduction to querying evolutionary data across multiple sources that publish orthology information in RDF, namely: The Orthologous MAtrix (OMA), the European Bioinformatics Institute (EBI) RDF platform, the Database of Orthologous Groups (OrthoDB) and the Microbial Genome Database (MBGD). We present four protocols in increasing order of complexity. In these protocols, we demonstrate through SPARQL queries how to retrieve pairwise orthologs, homologous groups, and hierarchical orthologous groups. Finally, we show how orthology information in different sources can be compared, through the use of federated SPARQL queries.

Information sources used by local police to estimate the scope and nature of sex trafficking

2019 ◽  
Vol 42 (6) ◽  
pp. 976-991
Author(s):  
Hyunjung Cheon ◽  
Charles M. Katz ◽  
Vincent J. Webb
Keyword(s):  
Sex Trafficking ◽  
Policy Implications ◽  
Data Sources ◽  
Sources Of Information ◽  
Multiple Sources ◽  
Content Type ◽  
Special Unit ◽  
Local Police ◽  
Police Agencies ◽  
The Usa

Purpose Although trafficking of persons for commercial sex has been increasingly recognized as a community level problem most estimates of the prevalence of sex trafficking in the USA are made by federal entities and vary depending on the data sources used. Little is known about how local police agencies assess and understand sex trafficking in their own communities. The paper aims to discuss this issue. Design/methodology/approach To help fill this gap, the current study using survey data from a sample of local police agencies across the USA (n=72) examines law enforcement agencies’ knowledge of and experience with addressing local sex trafficking problems in their jurisdiction. Findings The majority of police agencies reported that sex trafficking is a problem in their jurisdictions and that they have a special unit that has a primary responsibility for addressing sex trafficking issues. Agencies with a special unit tend to use multiple sources of information including official record, intelligence data and personal experience to estimate the community’s trafficking problems when compared to agencies without a unit; however, most of agencies primarily depend on their professional experience. Originality/value This is the first study to examine the data sources used by local police agencies to estimate the scope and nature of their community’s sex trafficking problem, and the findings have important policy implications for understanding the reliability and validity of these estimates, and for their potential use to develop and implement data driven responses to sex trafficking problems.

Tailoring data source distributions for fairness-aware data integration

2021 ◽  
Vol 14 (11) ◽  
pp. 2519-2532
Author(s):  
Fatemeh Nargesian ◽  
Abolfazl Asudeh ◽  
H. V. Jagadish
Keyword(s):  
Optimal Solution ◽  
Cost Effective ◽  
Data Sources ◽  
Data Sets ◽  
Multiple Sources ◽  
Data Set ◽  
Demographic Groups ◽  
Reward Function ◽  
Effective Manner ◽  
Data Source

Data scientists often develop data sets for analysis by drawing upon sources of data available to them. A major challenge is to ensure that the data set used for analysis has an appropriate representation of relevant (demographic) groups: it meets desired distribution requirements. Whether data is collected through some experiment or obtained from some data provider, the data from any single source may not meet the desired distribution requirements. Therefore, a union of data from multiple sources is often required. In this paper, we study how to acquire such data in the most cost effective manner, for typical cost functions observed in practice. We present an optimal solution for binary groups when the underlying distributions of data sources are known and all data sources have equal costs. For the generic case with unequal costs, we design an approximation algorithm that performs well in practice. When the underlying distributions are unknown, we develop an exploration-exploitation based strategy with a reward function that captures the cost and approximations of group distributions in each data source. Besides theoretical analysis, we conduct comprehensive experiments that confirm the effectiveness of our algorithms.

scholarly journals Progression of Cognitive-Affective States During Learning in Kindergarteners: Bringing Together Physiological, Observational and Performance Data

2020 ◽  
Vol 10 (7) ◽  
pp. 177
Author(s):  
Priyashri Kamlesh Sridhar ◽  
Suranga Nanayakkara
Keyword(s):  
Data Sources ◽  
Physiological Data ◽  
Affective States ◽  
Multiple Sources ◽  
Multiple Data ◽  
Combining Data ◽  
And Performance ◽  
And Mathematics ◽  
Future Work ◽  
Physiological Markers

It has been shown that combining data from multiple sources, such as observations, self-reports, and performance with physiological markers offers better insights into cognitive-affective states during the learning process. Through a study with 12 kindergarteners, we explore the role of utilizing insights from multiple data sources, as a potential arsenal to supplement and complement existing assessments methods in understanding cognitive-affective states across two main pedagogical approaches—constructionist and instructionist—as children explored learning a chosen Science, Technology, Engineering and Mathematics (STEM) concept. We present the trends that emerged across pedagogies from different data sources and illustrate the potential value of additional data channels through case illustrations. We also offer several recommendations for such studies, particularly when collecting physiological data, and summarize key challenges that provide potential avenues for future work.

Supporting the Development of Clinical Reasoning of Preprofessional Novices in Dysphagia Management

2019 ◽  
Vol 40 (03) ◽  
pp. 151-161 ◽  
Author(s):  
Sebastian Doeltgen ◽  
Stacie Attrill ◽  
Joanne Murray
Keyword(s):  
Clinical Reasoning ◽  
Clinical Decision Making ◽  
Management Practice ◽  
Clinical Decision ◽  
Assessment Process ◽  
Evidence Based ◽  
Sources Of Information ◽  
Multiple Sources ◽  
Implicit Processing ◽  
Reasoning Skills

AbstractProficient clinical reasoning is a critical skill in high-quality, evidence-based management of swallowing impairment (dysphagia). Clinical reasoning in this area of practice is a cognitively complex process, as it requires synthesis of multiple sources of information that are generated during a thorough, evidence-based assessment process and which are moderated by the patient's individual situations, including their social and demographic circumstances, comorbidities, or other health concerns. A growing body of health and medical literature demonstrates that clinical reasoning skills develop with increasing exposure to clinical cases and that the approaches to clinical reasoning differ between novices and experts. It appears that it is not the amount of knowledge held, but the way it is used, that distinguishes a novice from an experienced clinician. In this article, we review the roles of explicit and implicit processing as well as illness scripts in clinical decision making across the continuum of medical expertise and discuss how they relate to the clinical management of swallowing impairment. We also reflect on how this literature may inform educational curricula that support SLP students in developing preclinical reasoning skills that facilitate their transition to early clinical practice. Specifically, we discuss the role of case-based curricula to assist students to develop a meta-cognitive awareness of the different approaches to clinical reasoning, their own capabilities and preferences, and how and when to apply these in dysphagia management practice.

Integration of statistical and administrative agricultural data from Namibia

2021 ◽  
pp. 1-22
Author(s):  
Emily Berg ◽  
Johgho Im ◽  
Zhengyuan Zhu ◽  
Colin Lewis-Beck ◽  
Jie Li
Keyword(s):  
Measurement Error ◽  
Data Collection ◽  
Administrative Data ◽  
Statistical Data ◽  
Data Sources ◽  
Extension Programs ◽  
Multiple Data ◽  
Administrative Agencies ◽  
Crop Area ◽  
Using Data

Statistical and administrative agencies often collect information on related parameters. Discrepancies between estimates from distinct data sources can arise due to differences in definitions, reference periods, and data collection protocols. Integrating statistical data with administrative data is appealing for saving data collection costs, reducing respondent burden, and improving the coherence of estimates produced by statistical and administrative agencies. Model based techniques, such as small area estimation and measurement error models, for combining multiple data sources have benefits of transparency, reproducibility, and the ability to provide an estimated uncertainty. Issues associated with integrating statistical data with administrative data are discussed in the context of data from Namibia. The national statistical agency in Namibia produces estimates of crop area using data from probability samples. Simultaneously, the Namibia Ministry of Agriculture, Water, and Forestry obtains crop area estimates through extension programs. We illustrate the use of a structural measurement error model for the purpose of synthesizing the administrative and survey data to form a unified estimate of crop area. Limitations on the available data preclude us from conducting a genuine, thorough application. Nonetheless, our illustration of methodology holds potential use for a general practitioner.

Exploring young learners’ L2 development and perceptions of mixed-age and same-age peer interactions in EFL mixed-age classrooms

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Tomas Kos
Keyword(s):  
Foreign Language ◽  
Peer Interactions ◽  
Language Instruction ◽  
Data Sources ◽  
Foreign Language Instruction ◽  
Young Learners ◽  
Multiple Data ◽  
L2 Development ◽  
Post Test ◽  
Mixed Age

Abstract Although foreign language instruction in mixed-age (M-A) is gaining popularity (Heizmann and Ries and Wicki 2015; Lau and Juby-Smith and Desbiens, 2017; Shahid Kazi and Moghal and Aziz 2018; Thurn 2011), the research is scarce. Drawing from multiple data sources, this study investigated to what extent do peer interactions among M-A and same-age (S-A) pairs aid L2 development and how students perceive their interactions. In this study, the same learners (N=24) aged between 10 and 12 interacted with the same and different age partners during common classroom lessons in two EFL classrooms. The results suggest that both S-A and M-A peer interactions aided L2 development. Although S-A pairs outperformed M-A pairs on the post-test, the results are not statistically significant. The analysis of students’ perceptions revealed that the majority of students prefer working in S-A to M-A pairs. In addition to age/proficiency differences, factors such as students’ relationships and perceptions of one’s own and partner’s proficiency greatly impact how they interact with one another.

Sign in / Sign up

Export Citation Format

Share Document