Investigating Integral Reinforcement Learning to Achieve Asymptotic Stability in Underactuated Mechanical Systems

This letter introduces an innovative data-driven integral reinforcement learning (IRL) algorithm for the control of a class of underactuated mechanical systems. We propose a novel value function that allows shaping and learning the potential energy of an underactuated system and to drive it to a desired closed-loop potential energy. Consequently, we derive an actor-control policy that ensures asymptotic stability. In addition, we propose to parameterize the value function with a multi-layered perceptron (with 0, 1, and 2 hidden layers), exploring various parameter configurations. Eventually, we assess the performance of the proposed IRL through simulations and experimental results, thus confirming the practical effectiveness of the control design approach.

Paper

Full text

PDF

Investigating Integral Reinforcement Learning to Achieve Asymptotic Stability in Underactuated Mechanical Systems

Semantic Scholar · Engineering · 2024

Abstract

This letter introduces an innovative data-driven integral reinforcement learning (IRL) algorithm for the control of a class of underactuated mechanical systems. We propose a novel value function that allows shaping and learning the potential energy of an underactuated system and to drive it to a desired closed-loop potential energy. Consequently, we derive an actor-control policy that ensures asymptotic stability. In addition, we propose to parameterize the value function with a multi-layered perceptron (with 0, 1, and 2 hidden layers), exploring various parameter configurations. Eventually, we assess the performance of the proposed IRL through simulations and experimental results, thus confirming the practical effectiveness of the control design approach.

Similar papers

© 2026 NYSGPT2525 LLC