PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning Projects
This addresses a practical infrastructure problem for researchers in offline reinforcement learning, enabling more efficient dataset management and sharing, though it is incremental as it builds on existing data formats and tools.
The paper tackles the lack of standardized infrastructure for managing and sharing datasets in offline reinforcement learning, introducing PyTupli as a scalable tool that streamlines creation, storage, and dissemination of benchmark environments and tuple datasets to enhance collaboration and reproducibility.
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.