Related papers: dagger: A Python Framework for Reproducible Machin…
Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute. However, as frameworks specialize performance optimization to patterns in popular networks, they…
Reproducibility is a core requirement of modern scientific research. For computational research, reproducibility means that code should produce the same results, even when run on different systems. A standard approach to ensuring…
Many research fields are currently reckoning with issues of poor levels of reproducibility. Some label it a "crisis", and research employing or building Machine Learning (ML) models is no exception. Issues including lack of transparency,…
Programming Language Processing (PLP) using machine learning has made vast improvements in the past few years. Increasingly more people are interested in exploring this promising field. However, it is challenging for new researchers and…
Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous or uninformative outputs, the pipeline may fail or produce…
Reproducibility is one of the core dimensions that concur to deliver Trustworthy Artificial Intelligence. Broadly speaking, reproducibility can be defined as the possibility to reproduce the same or a similar experiment or method, thereby…
Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires…
In this paper, we introduce ChainerRL, an open-source deep reinforcement learning (DRL) library built using Python and the Chainer deep learning framework. ChainerRL implements a comprehensive set of DRL algorithms and techniques drawn from…
To encourage the development of methods with reproducible and robust training behavior, we propose a challenge paradigm where competitors are evaluated directly on the performance of their learning procedures rather than pre-trained agents.…
Empirical research plays a fundamental role in the machine learning domain. At the heart of impactful empirical research lies the development of clear research hypotheses, which then shape the design of experiments. The execution of…
The robotics research field lacks formalized definitions and frameworks for evaluating advanced capabilities including generalizability (the ability for robots to perform tasks under varied contexts) and reproducibility (the performance of…
Deep learning has shown impressive performance on challenging perceptual tasks and has been widely used in software to provide intelligent services. However, researchers found deep neural networks vulnerable to adversarial examples. Since…
Imitation learning (IL) has shown strong potential for contact-rich precision insertion tasks. However, its practical deployment is often hindered by covariate shift and the need for continuous expert monitoring to recover from failures…
Generalist robot policies that can perform many tasks typically require extensive expert data or simulations for training. In this work, we propose a novel Data-Efficient multitask DAgger framework that distills a single multitask policy…
Interactive Imitation Learning deals with training a novice policy from expert demonstrations in an online fashion. The established DAgger algorithm trains a robust novice policy by alternating between interacting with the environment and…
In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or…
Deep Generative Machine Learning Models (DGMs) have been growing in popularity across the design community thanks to their ability to learn and mimic complex data distributions. DGMs are conventionally trained to minimize statistical…
In recent years, the research community, but also the general public, has raised serious questions about the reproducibility and replicability of scientific work. Since many studies include some kind of computational work, these issues are…
The field of deep learning is experiencing a trend towards producing reproducible research. Nevertheless, it is still often a frustrating experience to reproduce scientific results. This is especially true in the machine learning community,…
As reinforcement learning (RL) achieves more success in solving complex tasks, more care is needed to ensure that RL research is reproducible and that algorithms herein can be compared easily and fairly with minimal bias. RL results are,…