Details
| Original language | English |
|---|---|
| Title of host publication | The 16th European Workshop on Reinforcement Learning (EWRL 2023) |
| Publication status | Accepted/In press - 17 Sept 2023 |
| Event | European Workshop on Reinforcement Learning 2023 - Brüssel Duration: 13 Sept 2023 → 16 Sept 2023 https://ewrl.wordpress.com/ewrl16-2023/ |
Abstract
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
The 16th European Workshop on Reinforcement Learning (EWRL 2023). 2023.
Research output: Chapter in book/report/conference proceeding › Conference abstract › Research › peer review
}
TY - CHAP
T1 - A Patterns Framework for Incorporating Structure in Deep Reinforcement Learning
AU - Mohan, Aditya
AU - Zhang, Amy
AU - Lindauer, Marius
PY - 2023/9/17
Y1 - 2023/9/17
N2 - 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.
AB - 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.
KW - cs.LG
M3 - Conference abstract
BT - The 16th European Workshop on Reinforcement Learning (EWRL 2023)
T2 - European Workshop on Reinforcement Learning 2023
Y2 - 13 September 2023 through 16 September 2023
ER -