We address two domains of skill transfer problems encountered by an autonomous robot: within-domain adaptation and cross-domain transfer. Our aim is to provide skill representations which enable transfer in each problem classification. As such, we explore two approaches to skill representation which address each problem classification separately. The first representation, based on mimicking, encodes the full demonstration and is well suited for within-domain adaptation. The second representation is based on imitation and serves to encode a set of key points along the trajectory, which represent the goal points most relevant to the successful completion of the skill. This representation enables both within-domain and cross-domain transfer. A planner is then applied to these constraints, generating a domain-specific trajectory which addresses the transfer task.

The goal of this research is to enable robots to learn new things from everyday people. For years, the AI and Robotics community has sought to enable robots to efficiently learn new skills from a knowledgeable human trainer, and prior work has focused on several important technical problems. This vast amount of research in the field of robot Learning by Demonstration has by and large only been evaluated with expert humans, typically the system's designer. Thus, neglecting a key point that this interaction takes place within a social structure that can guide and constrain the learning problem. %Moreover, we We believe that addressing this point will be essential for developing systems that can learn from everyday people that are not experts in Machine Learning or Robotics. Our work focuses on new research questions involved in letting robots learn from everyday human partners (e.g., What kind of input do people want to provide a machine learner? How does their mental model of the learning process affect this input? What interfaces and interaction mechanisms can help people provide better input from a machine learning perspective?) Often our research begins with an investigation into the feasibility of a particular machine learning interaction, which leads to a series of research questions around re-designing both the interaction and the algorithm to better suit learning with end-users. We believe this equal focus on both the Machine Learning and the HRI contributions are key to making progress toward the goal of machines learning from humans. In this abstract we briefly overview four different projects that highlight our HRI approach to the problem of Learning from Demonstration.

Socially assistive robotics (SAR) has the potential to combinethe massive replication and standardization of computertechnology with the benefits of learning in a social and tangible(hands-on) context. We are developing HRI methodsfor SAR systems designed to supplement the efforts of humanteachers to personalize education in the classroom. Thisabstract defines and proposes solutions to the computationalchallenges inherent in accomplishing differentiated and personalizededucation utilizing SAR in real-world classrooms. We aim to design robotic systems that are compelling, assistchildren in achieving educational goals, and mitigate developmentalchallenges in a classroom context. To do so, ourapproach must be deeply informed by the needs of our targetusers, children, at all stages of development, and mustadapt to a variety of special needs. In this abstract, we discussmotivation and computational methods for personalizedSAR systems for general, special needs, and mixed multichildeducation contexts. We focus on the personalizationand adaptation of curriculum, feedback, and robot character.

The emergence of online crowdsourcing sites, online work platforms, and evenMassive Open Online Courses (MOOCs), has created an increasing need for reliably evaluating the skills of the participating users in a scalable way.Many platforms already allow users to take online tests and verify their skills, but the existing approaches face many problems. First of all, cheating is very common in online testing without supervision, as the test questions often "leak" and become easily available online together with the answers.Second, technical skills, such as programming, require the tests to be frequently updated in order to reflect the current state-of-the-art. Third,there is very limited evaluation of the tests themselves, and how effectively they measure the skill that the users are tested for. In this paper, we present a Scalable Testing and Evaluation Platform (STEP),that allows continuous generation and evaluation of test questions. STEP leverages already available content, on Question Answering sites such as StackOverflow and re-purposes these questions to generate tests. The system utilizes a crowdsourcing component for the editing of the questions, while it uses automated techniques for identifying promising QA threads that can be successfully re-purposed for testing. This continuous question generation decreases the impact of cheating and also creates questions that are closer to the real problems that the skill holder is expected to solve in real life.STEP also leverages the use of Item Response Theory to evaluate the quality of the questions. We also use external signals about the quality of the workers.These identify the questions that have the strongest predictive ability in distinguishing workers that have the potential to succeed in the online job marketplaces. Existing approaches contrast in using only internal consistency metrics to evaluate the questions. Finally, our system employs an automatic "leakage detector" that queries the Internet to identify leaked versions of our questions. We then mark these questions as "practice only," effectively removing them from the pool of questions used for evaluation. Our experimental evaluation shows that our system generates questions of comparable or higher quality compared to existing tests, with a cost of approximately 3-5 dollars per question, which is lower than the cost of licensing questions from existing test banks.

Welcome to the Second AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2014) held November 2-4, 2014, in Pittsburgh, Pennsylvania. This conference is an opportunity to build on the success of the First AAAI Human Computation and Crowdsourcing conference, and to promote the best scholarship in this vibrant and fast emerging, multidisciplinary area. The conference also comes on the heels of four HCOMP workshops, including two workshops hosted at the annual AAAI conference. The HCOMP conference is designed to be a venue for exchanging ideas and developments on principles, experiments, and implementations of systems that rely on programmatic access to human intellect to perform some aspect of computation, or where human perception, knowledge, reasoning, or coordinated activity contributes to the operation of larger systems and applications. Topics relevant to the discipline of human computation and crowdsourcing include human-computer interaction (HCI), computer-supported collaborative work (CSCW), cognitive psychology, organizational behavior, economics, information retrieval, databases, computer systems and programming languages, and optimization.

Increasingly social networks are being used for citizen science, where members of the public contribute knowledge to scientific endeavours. Tasks can be presented and solved using human computation, termed groupsourcing, with users benefiting from community tuition and experts gaining knowledge from the crowd. This paper gives details of a prototype that utilises groupsourcing to solve image classification tasks, to support social learning and to facilitate knowledge discovery in the domain of marine biology.

Kristen Grauman is an associate professor in the Department of Computer Science at the University of Texas at Austin. Her research in computer vision and machine learning focuses on visual search and object recognition. Before joining the University of Texas at Austin in 2007, she received her Ph.D. in the Electrical Engineering and Computer Science department at the Massachusetts Institute of Technology, in the Computer Science and Artificial Intelligence Laboratory. She is an Alfred P. Sloan Research Fellow and Microsoft Research New Faculty Fellow, a recipient of NSF CAREER and ONR Young Investigator awards, the Regents' Outstanding Teaching Award from the University of Texas System in 2012, the PAMI Young Researcher Award in 2013, the 2013 Computers and Thought Award from the International Joint Conference on Artificial Intelligence, and a Presidential Early Career Award for Scientists and Engineers (PECASE) in 2013. She and her collaborators were recognized with the CVPR Best Student Paper Award in 2008 for their work on hashing algorithms for large-scale image retrieval, and the Marr Best Paper Prize at ICCV in 2011 for their work on modeling relative visual attributes.

One way of teaching grammar, namely morphology and syntax, is to visualize sentences as diagrams capturing relationships between words. Similarly, such relationships are captured in a more complex way in treebanks serving as key building stones in modern natural language processing. However, building them is very time consuming, thus we have been seeking for an alternative cheaper and faster way, like crowdsourcing. The purpose of our work is to explore possibility to get sentence diagrams produced by students and teachers. In our pilot study, the object language is Czech, where sentence diagrams are part of elementary school curriculum.

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult problems within a consistent framework. We discuss some challenges posed by the arcade learning environment which do not manifest in simpler environments. We then provide a comparison of model-free, linear learning algorithms on this challenging problem set.

Many machine learning approaches are characterized by information constraints on how they interact with the training data. These include memory and sequential access constraints (e.g. fast first-order methods to solve stochastic optimization problems); communication constraints (e.g. distributed learning); partial access to the underlying data (e.g. missing features and multi-armed bandits) and more. However, currently we have little understanding how such information constraints fundamentally affect our performance, independent of the learning problem semantics. For example, are there learning problems where any algorithm which has small memory footprint (or can use any bounded number of bits from each example, or has certain communication constraints) will perform worse than what is possible without such constraints? In this paper, we describe how a single set of results implies positive answers to the above, for several different settings.