Mutual information weighing for probabilistic movement primitives
Cita com:
hdl:2117/385189
Tipus de documentText en actes de congrés
Data publicació2022
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 4.0 Internacional
Abstract
Reinforcement Learning (RL) of trajectory data has been used in several fields, and it is of relevance in robot motion learning, in which sampled trajectories are run and their outcome is evaluated with a reward value. The responsibility on the performance of a task can be associated to the trajectory as a whole, or distributed throughout its points (timesteps). In this work, we present a novel method for attributing the responsibility of the rewards to each time-step separately by using Mutual Information (MI) to bias the model fitting of a trajectory.
CitacióColome, A.; Torras, C. Mutual information weighing for probabilistic movement primitives. A: Catalonian Conference on Artificial Intelligence. "Frontiers in Artificial Intelligence and Applications vol 356". 2022, p. 365-368. ISBN 978-1-64368-327-0. DOI 10.3233/FAIA220359.
ISBN978-1-64368-327-0
Versió de l'editorhttps://ebooks.iospress.nl/doi/10.3233/FAIA220359
Col·leccions
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
2647-Mutual-Inf ... ic-Movement-Primitives.pdf | 204,2Kb | Visualitza/Obre |