Continual Reinforcement Learning for Quadruped Robot Locomotion

The ability to learn continuously is crucial for a robot to achieve a high level of intelligence and autonomy. In this paper, we consider continual reinforcement learning (RL) for quadruped robots, which includes the ability to continuously learn sub-sequential tasks (plasticity) and maintain perfor...

Descripció completa

Dades bibliogràfiques

Autors principals:	Sibo Gai, Shangke Lyu, Hongyin Zhang, Donglin Wang
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2024-01-01
Col·lecció:	Entropy
Matèries:	continual learning quadruped robot locomotion reinforcement learning plasticity entropy
Accés en línia:	https://www.mdpi.com/1099-4300/26/1/93
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!