CORL: Research-oriented Deep Offline Reinforcement Learning Library
This library addresses the need for standardized, reliable tools for researchers working on offline reinforcement learning, though it is incremental as it builds on existing methods and datasets.
The researchers developed CORL, an open-source library providing thoroughly benchmarked single-file implementations of deep offline and offline-to-online reinforcement learning algorithms, with features like experiment tracking and reliability ensured through benchmarking on D4RL datasets.
CORL is an open-source library that provides thoroughly benchmarked single-file implementations of both deep offline and offline-to-online reinforcement learning algorithms. It emphasizes a simple developing experience with a straightforward codebase and a modern analysis tracking tool. In CORL, we isolate methods implementation into separate single files, making performance-relevant details easier to recognize. Additionally, an experiment tracking feature is available to help log metrics, hyperparameters, dependencies, and more to the cloud. Finally, we have ensured the reliability of the implementations by benchmarking commonly employed D4RL datasets providing a transparent source of results that can be reused for robust evaluation tools such as performance profiles, probability of improvement, or expected online performance.