English

Equivariant Reinforcement Learning under Partial Observability

Robotics 2024-08-27 v1 Artificial Intelligence Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@article{arxiv.2408.14336,
  title  = {Equivariant Reinforcement Learning under Partial Observability},
  author = {Hai Nguyen and Andrea Baisero and David Klee and Dian Wang and Robert Platt and Christopher Amato},
  journal= {arXiv preprint arXiv:2408.14336},
  year   = {2024}
}

Comments

Conference on Robot Learning, 2023

R2 v1 2026-06-28T18:24:05.084Z