相关论文: Learning from Imperfect Demonstrations via Adversa…

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to…

A burgeoning paradigm in algorithm design is the field of algorithms with predictions, in which algorithms can take advantage of a possibly-imperfect prediction of some aspect of the problem. While much work has focused on using predictions…

Imitation learning offers a promising framework for enabling robots to acquire diverse skills from human users. However, most imitation learning algorithms assume access to high-quality demonstrations an unrealistic expectation when…

In this paper we investigate the vulnerability that facial recognition systems present to adversarial examples by introducing a new methodology from the attacker perspective. The technique is based on the use of the autoencoder latent…

We initiate an investigation of learning tasks in a setting where the learner is given access to two competing provers, only one of which is honest. Specifically, we consider the power of such learners in assessing purported properties of…

The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on…

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial…

Machine learning is used for inference and decision making in wearable sensor systems. However, recent studies have found that machine learning algorithms are easily fooled by the addition of adversarial perturbations to their inputs. What…

In this work we propose a novel end-to-end imitation learning approach which combines natural language, vision, and motion information to produce an abstract representation of a task, which in turn is used to synthesize specific motion…

Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a reliable confidence value allowing to detect misclassifications. This limitation is at the heart of what is known as an…

In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data. However, standard IL algorithms consider these datasets as homogeneous, thereby…

This paper studies the performative policy learning problem, where agents adjust their features in response to a released policy to improve their potential outcomes, inducing an endogenous distribution shift. There has been growing interest…

The robot learning community has made great strides in recent years, proposing new architectures and showcasing impressive new capabilities; however, the dominant metric used in the literature, especially for physical experiments, is…

Learning a reward function from demonstrations suffers from low sample-efficiency. Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in…

Key challenges for the deployment of reinforcement learning (RL) agents in the real world are the discovery, representation and reuse of skills in the absence of a reward function. To this end, we propose a novel approach to learn a…

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited…

Recent advances in learning-based robot manipulation have produced policies with remarkable capabilities. Yet, reliability at deployment remains a fundamental barrier to real-world use, where distribution shift, compounding errors, and…

In real-world applications, one often encounters ambiguously labeled data, where different annotators assign conflicting class labels. Partial-label learning allows training classifiers in this weakly supervised setting, where…

Humans generally teach their fellow collaborators to perform tasks through a small number of demonstrations. The learnt task is corrected or extended to meet specific task goals by means of coaching. Adopting a similar framework for…