Members of the AIRL lab at Imperial College, and authors of the reported work in this blog post. From left to right: Bryan Lim, Dr Antoine Cully (director of the AIRL lab), Manon Flageat, Luca Grillotti, Dr Simón C Smith, and Maxime Allard. Learning and finding different solutions to the same problem is commonly associated with creativity and adaptation, which are important characteristics of intelligence. In the AIRL lab at Imperial College, we believe in the importance of diversity in learning algorithms. With this focus in mind, we develop learning algorithms known as Quality-Diversity algorithms.

We consider planning problems with time windows, in which the availability of discrete resources is time constrained. We develop a novel heuristic that addresses specifically the difficulty of coordinating actions within time windows. The heuristic is based on solving a temporally relaxed problem and measuring the magnitude by which the relaxed solution violates the time window constraints. Applied in a state-space search planner, the heuristic reduces the number of dead-ends encountered during search, and improves planner coverage.

A reimagined version of Mattel Electronics' Intellivision is scheduled to be released this fall. To help put the finishing touches on the Amico game console, Intellivision Entertainment -- a separate entity than Mattel that owns the Intellivision brand -- has hired J. Allard as the company's global managing director. Allard is one of the fathers of Microsoft's Xbox division, having served as chief experience officer and chief technology officer. He helped launch the original Xbox, Xbox Live, the Xbox 360 and Xbox Live Arcade. Intellivision is hoping that the exec's success carries over to its family-friendly console. It's not clear which aspects of the console Allard will be helping to improve, but his industry knowledge could be a benefit.

Data sets are often modeled as point clouds in $R^D$, for $D$ large. It is often assumed that the data has some interesting low-dimensional structure, for example that of a $d$-dimensional manifold $M$, with $d$ much smaller than $D$. When $M$ is simply a linear subspace, one may exploit this assumption for encoding efficiently the data by projecting onto a dictionary of $d$ vectors in $R^D$ (for example found by SVD), at a cost $(n+D)d$ for $n$ data points. When $M$ is nonlinear, there are no "explicit" constructions of dictionaries that achieve a similar efficiency: typically one uses either random dictionaries, or dictionaries obtained by black-box optimization. In this paper we construct data-dependent multi-scale dictionaries that aim at efficient encoding and manipulating of the data. Their construction is fast, and so are the algorithms that map data points to dictionary coefficients and vice versa. In addition, data points are guaranteed to have a sparse representation in terms of the dictionary. We think of dictionaries as the analogue of wavelets, but for approximating point clouds rather than functions.