This report describes our proposed solution for the second AI Olympics competition held at IROS 2024. Our solution is based on a recent Model-Based Reinforcement Learning algorithm named MC-PILCO. Besides briefly reviewing the algorithm, we discuss the most critical aspects of the MC-PILCO implementation in the tasks at hand.
Cite
@article{arxiv.2409.05811,
title = {Learning control of underactuated double pendulum with Model-Based Reinforcement Learning},
author = {Niccolò Turcato and Alberto Dalla Libera and Giulio Giacomuzzo and Ruggero Carli and Diego Romeres},
journal= {arXiv preprint arXiv:2409.05811},
year = {2024}
}