We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional embedding of the policy on a reproducing kernel Hilbert space (RKHS). The usage of RKHS based methods allows us to derive strong theoretical guarantees on the expected return of the reconstructed policy. Such guarantees are typically lacking in black-box models, but are very desirable in tasks requiring stability and convergence guarantees. We conduct several experiments on classic RL domains. The results confirm that the policies can be robustly represented in a low-dimensional space while the embedded policy incurs almost no decrease in returns.

Gifted students have a higher capabilities of understanding and learning. They are characterized by a high level of attention and a high performance in the classroom. Gifted children are defined in this paper as children who have a performance higher than the average group (59.64%). In order to predict gifted students from normal students, we conducted an experiment where 17 pupils have voluntarily participated in this study. We collected different types of data (gender, age, performance, initial average in math and EEG mental states) in a web platform to learn mathematics called NetMath. Participants were invited to respond to top-level exercises on the four basic operations in decimals. We trained different machine learning algorithms to predict gifted students. Our first results show that the decision tree could predict gifted students with an accuracy of 76.88%. Using J48 trees, we noticed also that two relevant features could determine gifted children: the relaxation extracted from EEG headset and the characteristic of strong student. A strong student is defined as a student who obtained a mean higher than the group’s mean in the first step evaluation in class.

Narratives are powerful because of their impact on our emotional experiences. Recent years have witnessed significant advances in affective computing and intelligent interaction, presenting a broad range of opportunities for enhancing the design, implementation, and adaptivity of interactive narratives. This paper presents preliminary work examining story-centric games and interactive narratives from the perspective of psychological theories of emotion, with a particular focus on player affect. We examine the sources and duration of player emotion, social facets of emotion, players’ individual differences in emotion, and meta-emotions. Recommendations and future directions for research on player emotion in interactive narratives are discussed.

This paper first sketches a living lab infrastructure installed in an alternative housing unit built to host 10 people with traumatic brain injury. It then presents the first research project in progress within this living lab. This interdisciplinary project aims at designing, implementing, deploying, and assessing a personalized assistive technology (PAT). Based on the needs and expectations expressed by the residents, their caregivers and their families, a cooking assistant appeared as one of the best suited PAT to foster residents autonomy and social participation. The resulting PAT will rely on pervasive computing and ambient intelligence. It will then be personalized according to each participant's capacities and specific cognitive impairments. The impact of the assistant on autonomy and quality of life will then be measured. The overall organizational impact of such assistive technology will be also documented and evaluated.

In web search, users queries are formulated using only few terms and term-matching retrieval functions could fail at retrieving relevant documents. Given a user query, the technique of query expansion (QE) consists in selecting related terms that could enhance the likelihood of retrieving relevant documents. Selecting such expansion terms is challenging and requires a computational framework capable of encoding complex semantic relationships. In this paper, we propose a novel method for learning, in a supervised way, semantic representations for words and phrases. By embedding queries and documents in special matrices, our model disposes of an increased representational power with respect to existing approaches adopting a vector representation. We show that our model produces high-quality query expansion terms. Our expansion increase IR measures beyond expansion from current word-embeddings models and well-established traditional QE methods.

Restricted Boltzmann machines (RBMs) are powerful machine learning models, but learning and some kinds of inference in the model require sampling-based approximations, which, in classical digital computers, are implemented using expensive MCMC. Physical computation offers the opportunity to reduce the costof sampling by building physical systems whose natural dynamics correspond to drawing samples from the desired RBM distribution. Such a system avoids the burn-in and mixing cost of a Markov chain. However, hardware implementations of this variety usually entail limitations such as low-precision and limited range of the parameters and restrictions on the size and topology of the RBM. We conduct software simulations to determine how harmful each of these restrictions is. Our simulations are based on the D-Wave Two computer, but the issues we investigate arise in most forms of physical computation.Our findings suggest that designers of new physical computing hardware and algorithms for physical computers should focus their efforts on overcoming the limitations imposed by the topology restrictions of currently existing physical computers.