Learning global control of underactuated systems with Model-Based Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Turcato, Niccolò, Calì, Marco, Libera, Alberto Dalla, Giacomuzzo, Giulio, Carli, Ruggero, Romeres, Diego
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913785893093376
author Turcato, Niccolò
Calì, Marco
Libera, Alberto Dalla
Giacomuzzo, Giulio
Carli, Ruggero
Romeres, Diego
author_facet Turcato, Niccolò
Calì, Marco
Libera, Alberto Dalla
Giacomuzzo, Giulio
Carli, Ruggero
Romeres, Diego
contents This short paper describes our proposed solution for the third edition of the "AI Olympics with RealAIGym" competition, held at ICRA 2025. We employed Monte-Carlo Probabilistic Inference for Learning Control (MC-PILCO), an MBRL algorithm recognized for its exceptional data efficiency across various low-dimensional robotic tasks, including cart-pole, ball \& plate, and Furuta pendulum systems. MC-PILCO optimizes a system dynamics model using interaction data, enabling policy refinement through simulation rather than direct system data optimization. This approach has proven highly effective in physical systems, offering greater data efficiency than Model-Free (MF) alternatives. Notably, MC-PILCO has previously won the first two editions of this competition, demonstrating its robustness in both simulated and real-world environments. Besides briefly reviewing the algorithm, we discuss the most critical aspects of the MC-PILCO implementation in the tasks at hand: learning a global policy for the pendubot and acrobot systems.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning global control of underactuated systems with Model-Based Reinforcement Learning
Turcato, Niccolò
Calì, Marco
Libera, Alberto Dalla
Giacomuzzo, Giulio
Carli, Ruggero
Romeres, Diego
Robotics
Artificial Intelligence
Machine Learning
This short paper describes our proposed solution for the third edition of the "AI Olympics with RealAIGym" competition, held at ICRA 2025. We employed Monte-Carlo Probabilistic Inference for Learning Control (MC-PILCO), an MBRL algorithm recognized for its exceptional data efficiency across various low-dimensional robotic tasks, including cart-pole, ball \& plate, and Furuta pendulum systems. MC-PILCO optimizes a system dynamics model using interaction data, enabling policy refinement through simulation rather than direct system data optimization. This approach has proven highly effective in physical systems, offering greater data efficiency than Model-Free (MF) alternatives. Notably, MC-PILCO has previously won the first two editions of this competition, demonstrating its robustness in both simulated and real-world environments. Besides briefly reviewing the algorithm, we discuss the most critical aspects of the MC-PILCO implementation in the tasks at hand: learning a global policy for the pendubot and acrobot systems.
title Learning global control of underactuated systems with Model-Based Reinforcement Learning
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.06721