Equivariant Reinforcement Learning under Partial Observability
Hai Huu Nguyen, Andrea Baisero, David Klee, Dian Wang, Robert Platt, Christopher Amato
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.
BibTeX
@inproceedings{
nguyen2023equivariant,
title={Equivariant Reinforcement Learning under Partial Observability},
author={Hai Huu Nguyen and Andrea Baisero and David Klee and Dian Wang and Robert Platt and Christopher Amato},
booktitle={7th Annual Conference on Robot Learning},
year={2023},
url={https://openreview.net/forum?id=AnDDMQgM7-}
}