RLDS:在强化学习中生成、共享和使用数据集的生态系统 (RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning)

Sabela Ramos,Sertan Girgin,Léonard Hussenot,Damien Vincent,Hanna Yakubovich,Daniel Toyama,Anita Gergely,Piotr Stanczyk,Raphael Marinier,Jeremiah Harmsen,Olivier Pietquin,Nikola Momchev

from arxiv, https://github.com/google-research/rlds

We introduce RLDS (Reinforcement Learning Datasets), an ecosystem for recording, replaying, manipulating, annotating and sharing data in the context of Sequential Decision Making (SDM) including Reinforcement Learning (RL), Learning from Demonstrations, Offline RL or Imitation Learning. RLDS enables not only reproducibility of existing research and easy generation of new datasets, but also accelerates novel research. By providing a standard and lossless format of datasets it enables to quickly test new algorithms on a wider range of tasks. The RLDS ecosystem makes it easy to share datasets without any loss of information and to be agnostic to the underlying original format when applying various data processing pipelines to large collections of datasets. Besides, RLDS provides tools for collecting data generated by either synthetic agents or humans, as well as for inspecting and manipulating the collected data. Ultimately, integration with TFDS facilitates the sharing of RL datasets with the research community.

翻译：我们引入了RLDS(加强学习数据集),这是一个用于记录、重播、操纵、说明和共享数据、包括强化学习(RL)、从演示中学习、离线RL或模拟学习(Smitation Learning)在内的按顺序决策(SDM)背景下的数据的生态系统。RLDS不仅能够重新复制现有的研究和轻松生成新的数据集,而且还加快了新式研究。它提供了一个标准和无损失的数据集格式,能够快速测试范围更广的任务领域的新算法。RLDS生态系统使得在不丢失任何信息的情况下共享数据集变得容易,并且在将各种数据处理管道应用于大量数据集收集时能够适应原始基本格式。此外,RLDS还提供了工具,用于收集合成物或人类生成的数据,以及检查和操纵所收集的数据。最终,与TFDS的整合有助于与研究界共享RL数据集。