Behavior policy learning: Learning multi-stage tasks via solution sketches and model-based controllers

Multi-stage tasks are a challenge for reinforcement learning methods, and require either specific task knowledge (e.g., task segmentation) or big amount of interaction times to be learned. In this paper, we propose Behavior Policy Learning (BPL) that effectively combines 1) only few solution sketche...

Descripción completa

Detalles Bibliográficos
Autores principales: Tsinganos, Konstantinos, Chatzilygeroudis, Konstantinos, Hadjivelichkov, Denis, Komninos, Theodoros, Dermatas, Evangelos, Kanoulas, Dimitrios
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Robotics and AI
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9597635/
https://www.ncbi.nlm.nih.gov/pubmed/36313244
http://dx.doi.org/10.3389/frobt.2022.974537

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9597635/
https://www.ncbi.nlm.nih.gov/pubmed/36313244
http://dx.doi.org/10.3389/frobt.2022.974537

Ejemplares similares