Journal
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH
Volume 75, Issue -, Pages 1401-1476Publisher
AI ACCESS FOUNDATION
Keywords
-
Categories
Funding
- Canada CIFAR AI Chair Program
- Canada Excellence Research Chairs Program
Ask authors/readers for more resources
This article provides a literature review of different formulations and approaches to continual reinforcement learning, discussing the perspective on why RL is suitable for studying continual learning, providing a taxonomy of different formulations and approaches, and discussing evaluation and future challenges.
In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We begin by discussing our perspective on why RL is a natural fit for studying continual learning. We then provide a taxonomy of different continual RL formulations by mathematically characterizing two key properties of non-stationarity, namely, the scope and driver non-stationarity. This offers a unified view of various formulations. Next, we review and present a taxonomy of continual RL approaches. We go on to discuss evaluation of continual RL agents, providing an overview of benchmarks used in the literature and important metrics for understanding agent performance. Finally, we highlight open problems and challenges in bridging the gap between the current state of continual RL and findings in neuroscience. While still in its early days, the study of continual RL has the promise to develop better incremental reinforcement learners that can function in increasingly realistic applications where non-stationarity plays a vital role. These include applications such as those in the fields of healthcare, education, logistics, and robotics.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available