Equivariant Reinforcement Learning under Partial Observability

Incorporating inductive biases is a promising approach for tackling challenging robot learning domains with sample-efficient solutions. This paper identifies partially observable domains where symmetries can be a useful inductive bias for efficient learning. Specifically, by encoding the equivarianc...

Full description

Saved in:
Bibliographic Details
Main Authors Nguyen, Hai, Baisero, Andrea, Klee, David, Wang, Dian, Platt, Robert, Amato, Christopher
Format Journal Article
LanguageEnglish
Published 26.08.2024
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Robotics
Online AccessGet full text

Cover

More Information
Summary:Incorporating inductive biases is a promising approach for tackling challenging robot learning domains with sample-efficient solutions. This paper identifies partially observable domains where symmetries can be a useful inductive bias for efficient learning. Specifically, by encoding the equivariance regarding specific group symmetries into the neural networks, our actor-critic reinforcement learning agents can reuse solutions in the past for related scenarios. Consequently, our equivariant agents outperform non-equivariant approaches significantly in terms of sample efficiency and final performance, demonstrated through experiments on a range of robotic tasks in simulation and real hardware.
DOI:10.48550/arxiv.2408.14336