RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms
Abstract
Learning a controller directly on the robot requires extreme sample efficiency. Model-based reinforcement learning (RL) methods are the most sample efficient, but they often suffer from a too long inference time to meet the robot control frequency requirements. In this paper, we address the sample efficiency and inference time challenges with two contributions. First, we define a general framework to deal with inference delays where the slow inference robot controller provides a sequence of actions to feed the control-hungry robotic platform without execution gaps. Then, we compare several RL algorithms in the light of this framework and propose RT-HCP, an algorithm that offers an excellent trade-off between performance, sample efficiency and inference time. We validate the superiority of RT-HCP with experiments where we learn a controller directly on a simple but high frequency FURUTA pendulum platform. Code: github.com/elasriz/RTHCP
Cite
@article{arxiv.2509.06714,
title = {RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms},
author = {Zakariae El Asri and Ibrahim Laiche and Clément Rambour and Olivier Sigaud and Nicolas Thome},
journal= {arXiv preprint arXiv:2509.06714},
year = {2025}
}
Comments
IROS 2025