We formalize a framework to learn the Koopman operator from finite data trajectories of the dynamical system.
This is done by using proto-policies as modules to divide the tasks into simple sub-behaviours that can be shared.
We study the theoretical properties of a kernel ridge regression estimator based on such representation, for which we prove universal consistency and excess risk bounds.
Few-shot learning is a central problem in meta-learning, where learners must quickly adapt to new tasks given limited training data.
Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks.
Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks.
Among these, computing the inverse kinematics of a redundant robot arm poses a significant challenge due to the non-linear structure of the robot, the hard joint constraints and the non-invertible kinematics map.
One way to reach this goal is by modifying the data representation in order to meet certain fairness constraints.
However, these methods may perform poorly on heterogeneous environments of tasks, where the complexity of the tasks’ distribution cannot be captured by a single meta- parameter vector.
However, these methods may perform poorly on heterogeneous environments of tasks, where the complexity of the tasks' distribution cannot be captured by a single meta-parameter vector.
The Generative Adversarial Networks (GAN) framework is a well-established paradigm for probability matching and realistic sample generation.
Geometric representation learning has recently shown great promise in several machine learning settings, ranging from relational learning to language processing and generative models.
We derive task-adaptive structured meta-learning (TASML), a principled framework that yields task-specific objective functions by weighing meta-training data on target tasks.
To address the challenges, we propose Support-weighted Adversarial Imitation Learning (SAIL), a general framework that extends a given AIL algorithm with information derived from support estimation of the expert policies.
We propose and analyze a novel theoretical and algorithmic framework for structured prediction.
Within the framework of statistical learning theory it is possible to bound the minimum number of samples required by a learner to reach a target accuracy.
We propose Support-guided Adversarial Imitation Learning (SAIL), a generic imitation learning framework that unifies support estimation of the expert policy with the family of Adversarial Imitation Learning (AIL) algorithms.
We present a novel algorithm to estimate the barycenter of arbitrary probability distributions with respect to the Sinkhorn divergence.
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals.
We study the problem of learning-to-learn: inferring a learning algorithm that works well on tasks sampled from an unknown distribution.
We study the interplay between surrogate methods for structured prediction and techniques from multitask learning designed to leverage relationships between surrogate outputs.
We show that, in this setting, the LTL problem can be reformulated as a Least Squares (LS) problem and we exploit a novel meta- algorithm to efficiently solve it.
Structured prediction provides a general framework to deal with supervised problems where the outputs have semantically rich structure.
Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization.
Simulating the time-evolution of quantum mechanical systems is BQP-hard and expected to be one of the foremost applications of quantum computers.
In learning-to-learn the goal is to infer a learning algorithm that works well on a class of tasks sampled from an unknown meta distribution.
Numerous computer vision problems such as stereo depth estimation, object-class segmentation and foreground/background segmentation can be formulated as per-pixel image labeling tasks.
We report on an extensive study of the benefits and limitations of current deep learning approaches to object recognition in robot vision scenarios, introducing a novel dataset used for our investigation.
Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning techniques to impressive results in regression, classification, data-generation and reinforcement learning tasks.
A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem.
However, in practice assuming the tasks to be linearly related might be restrictive, and allowing for nonlinear structures is a challenge.
We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment.
The importance of depth perception in the interactions that humans have within their nearby space is a well established fact.
In this context a fundamental question is how to incorporate the tasks structure in the learning problem. We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including linear and non-linear approaches.
In this paper we investigate such possibility, while taking further steps in developing a computational vision system to be embedded on a robotic platform, the iCub humanoid robot.
Multi-task learning is a natural approach for computer vision applications that require the simultaneous solution of several distinct but related problems, e. g. object detection, classification, tracking of multiple agents, or denoising, to name a few.
In this paper we present and start analyzing the iCub World data-set, an object recognition data-set, we acquired using a Human-Robot Interaction (HRI) scheme and the iCub humanoid robot platform.