PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning Projects

TL;DR

PyTupli is a scalable Python tool that simplifies creating, sharing, and managing datasets and benchmarks for offline reinforcement learning, promoting collaboration and reproducibility.

Contribution

It introduces a standardized infrastructure for dataset management in offline RL, enabling easier sharing and curation of custom benchmarks.

Findings

Supports fine-grained filtering of datasets

Provides secure, scalable deployment options

Facilitates collaborative offline RL research

Abstract

Offline reinforcement learning (RL) has gained traction as a powerful paradigm for learning control policies from pre-collected data, eliminating the need for costly or risky online interactions. While many open-source libraries offer robust implementations of offline RL algorithms, they all rely on datasets composed of experience tuples consisting of state, action, next state, and reward. Managing, curating, and distributing such datasets requires suitable infrastructure. Although static datasets exist for established benchmark problems, no standardized or scalable solution supports developing and sharing datasets for novel or user-defined benchmarks. To address this gap, we introduce PyTupli, a Python-based tool to streamline the creation, storage, and dissemination of benchmark environments and their corresponding tuple datasets. PyTupli includes a lightweight client library with defined interfaces for uploading and retrieving benchmarks and data. It supports fine-grained filtering at both the episode and tuple level, allowing researchers to curate high-quality, task-specific datasets. A containerized server component enables production-ready deployment with authentication, access control, and automated certificate provisioning for secure use. By addressing key barriers in dataset infrastructure, PyTupli facilitates more collaborative, reproducible, and scalable offline RL research.