Search for: All records

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference framework incorporates the LLM-generated segmentation information to discover reusable skills by merging trajectory segments. To further control the trade-off between compression and reusability, we introduce a novel auxiliary objective based on the Minimum Description Length principle that helps guide this skill discovery process. Our results demonstrate that agents equipped with our method are able to discover skills that help accelerate learning and outperform baseline skill learning approaches on new long-horizon tasks in BabyAI, a grid world navigation environment, as well as ALFRED, a household simulation environment. 

Antarctic sea ice modeling has become essential due to the exacerbating effects of climate change on the region, with the aim of utilizing present and past data to predict the future. However, a setback lies in the grand scale of the data needed to make these predictions best, spanning both spatial and temporal axes. As a result, dimension reduction is necessary to capture the most important patterns of variability – a pre-processing step for future predictions. The utilization of Machine Learning tools, such as autoencoders, has been investigated as an alternative to linear dimension reduction methods, such as EOFs. Input data includes satellite observed gridded data in the Antarctic region from 1979 to 2022. Different versions of the autoencoder model are investigated, with varying components in its architecture, including activation function (linear and ReLU), bottleneck units (compressed dimensions), and added layers. It is found that the seven-layered and five-layered ReLU models outperform other configurations across all bottleneck units, including when compared with EOFs. These models also contain a higher explained variance ratio: at 11 compressed dimensions, the seven-layered autoencoder can capture 18.7% more variance than the 11 EOF modes explain. The ReLU activation function also allows the model to detect nonlinear patterns, providing an additional benefit to the improved RMSE and variance ratio. The findings demonstrate that the autoencoder model serves as a worthy alternative to EOFs, likely extracting more predictable variance in the sea ice field. The result is crucial for understanding sea ice spatiotemporal variability and its predictability in the Antarctic. 

The motivation of students to actively engage in course activities has significant impact on the outcome of academic courses. Prior studies have shown that innovative instructional interventions and course delivery methods have a vital role in boosting the motivation of students. Gamification tools aid course delivery by utilizing well established game design principles to enhance skill development, routine practice and self-testing. In this article, we present a study on how the use of a course gamification platform dubbed OneUp impacts the motivation of students in an online cyber security course. The study shows that more than 90% of the respondents agreed that OneUp has improved the effectiveness of the course delivery. In addition, 75% of the respondents want to use OneUp in their future courses. Furthermore, our analysis shows that OneUp has improved the median grade of students from B+ to A- compared to the same course delivered the previous year without using OneUp. 

Consider the scattering of a time-harmonic elastic plane wave by a periodic rigid surface. The elastic wave propagation is governed by the two-dimensional Navier equation. Based on a Dirichlet-to-Neumann (DtN) map, a transparent boundary condition (TBC) is introduced to reduce the scattering problem into a boundary value problem in a bounded domain. By using the finite element method, the discrete problem is considered, where the TBC is replaced by the truncated DtN map. A new duality argument is developed to derive the a posteriori error estimate, which contains both the finite element approximation error and the DtN truncation error. An a posteriori error estimate based adaptive finite element algorithm is developed to solve the elastic surface scattering problem. Numerical experiments are presented to demonstrate the effectiveness of the proposed method.