A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems
By Rafael Figueiredo Prudencio, Marcos Ricardo Omena de Albuquerque Máximo, Esther Luna Colombini. IEEE Transactions on Neural Networks and Learning Systems, 2022
424 citations recorded by the source corpus.
With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games from pixel observations, sustaining conversations with humans, and controlling robotic agents. However, there is still a wide range of domains inaccessible to RL due to the high cost and danger of interacting with the environment. Offline RL is a paradigm that learns exclusively from static datasets of previously collected interactions, making it feasible to extract policies from large and diverse training datasets. Effective offline RL algorithms have a much wider range of applications than online RL, being particularly appealing for real-world applications, such as education, healthcare, and robotics. In this work, we contribute with a unifying taxonomy to classify offline RL methods. Furthermore, we provide a comprehensive review of the latest algorithmic breakthroughs in the field using a unified notation as well as a review of existing benchmarks’ properties and shortcomings. Additionally, we provide a figure that summarizes the performance of each method and class of methods on different dataset properties, equipping researchers with the tools to decide which type of algorithm is best suited for the problem at hand and identify which classes of algorithms look the most promising. Finally, we provide our perspective on open problems and propose future research directions for this rapidly growing field.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/61e7a3d5606043594a8ce377870479f77a6b58c2
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- RLTF: Reinforcement Learning from Unit Test Feedback (2023, background): “Additionally, in contrast to domains such as healthcare, autonomous driving, and human-aligned in LLMs (Levine et al., 2020; Prudencio et al., 2023), where real-time interaction costs are high or data is difficult to obtain in real-time, the feedback from unit tests in the program synthesis task…”