A Patterns Framework for Incorporating Structure in Deep Reinforcement Learning

verfasst von

Aditya Mohan, Amy Zhang, Marius Lindauer

Abstract

Reinforcement Learning (RL), empowered by Deep Neural Networks (DNNs) for function approximation, has achieved notable success in diverse applications. However, its applicability to real-world scenarios with complex dynamics, noisy signals, and large state and action spaces remains limited due to challenges in data efficiency, generalization, safety guarantees, and interpretability, among other factors. To overcome these challenges, one promising avenue is to incorporate additional structural information about the problem into the RL learning process. Various sub-fields of RL have proposed methods for incorporating such inductive biases. We amalgamate these diverse methodologies under a unified framework, shedding light on the role of structure in the learning problem, and classify these methods into distinct patterns of incorporating structure that address different auxiliary objectives. By leveraging this comprehensive framework, we provide valuable insights into the challenges of integrating structure into RL and lay the groundwork for a design pattern perspective on RL research. This novel perspective paves the way for future advancements and aids in developing more effective and efficient RL algorithms that can better handle real-world scenarios.

Organisationseinheit(en)

Fachgebiet Maschinelles Lernen
Institut für Künstliche Intelligenz

Externe Organisation(en)

Meta AI
University of Texas at Austin

Typ

Abstract in Konferenzband

Publikationsdatum

17.09.2023

Publikationsstatus

Angenommen/Im Druck

Peer-reviewed

Ja

Ziele für nachhaltige Entwicklung

SDG 3 – Gute Gesundheit und Wohlergehen

Elektronische Version(en)

https://openreview.net/forum?id=KkKWsPLlAx (Zugang: Offen)