Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CORL: Research-oriented Deep Offline Reinforcement Learning Library

About

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.

Denis Tarasov, Alexander Nikulin, Dmitry Akimov, Vladislav Kurenkov, Sergey Kolesnikov• 2022

Related benchmarks

TaskDatasetResultRank
Offline Reinforcement LearningMaze2D medium v1
Normalized Return0.79
30
Offline Reinforcement LearningMaze2D large v1
Normalized Return2.26
30
Planning and Controlmaze2d-umaze v1 (100 episodes, 300 steps/ep)
Score0.36
16
Offline Reinforcement LearningAntMaze Medium-Diverse v2
Average Score0.008
14
Offline Reinforcement LearningAntMaze medium-play v2
Average Score0.00e+0
14
Offline Reinforcement LearningAntMaze large-play v2
D4RL Score0.00e+0
11
Offline Reinforcement LearningAntMaze large-diverse v2
D4RL Score0.00e+0
11
Showing 7 of 7 rows

Other info

Code

Follow for update