Learning robotic manipulation skills with multiple semantic goals by conservative curiosity-motivated exploration

Reinforcement learning (RL) empowers the agent to learn robotic manipulation skills autonomously. Compared with traditional single-goal RL, semantic-goal-conditioned RL expands the agent capacity to accomplish multiple semantic manipulation instructions. However, due to sparsely distributed semantic...

Descripción completa

Detalles Bibliográficos
Autores principales: Han, Changlin, Peng, Zhiyong, Liu, Yadong, Tang, Jingsheng, Yu, Yang, Zhou, Zongtan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10028088/
https://www.ncbi.nlm.nih.gov/pubmed/36960195
http://dx.doi.org/10.3389/fnbot.2023.1089270

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10028088/
https://www.ncbi.nlm.nih.gov/pubmed/36960195
http://dx.doi.org/10.3389/fnbot.2023.1089270

Ejemplares similares