Mitigating Catastrophic Forgetting in Robot Continual Learning: A Guided Policy Search Approach Enhanced With Memory-Aware Synapses

Complex operational scenarios increasingly demand that industrial robots sequentially resolve multiple interrelated problems to accomplish complex operational tasks, necessitating robots to have the capacity for not only learning through interaction with the environment but also for continual learni...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE robotics and automation letters 2024-12, Vol.9 (12), p.11242-11249
Hauptverfasser:	Dong, Qingwei, Zeng, Peng, He, Yunpeng, Wan, Guangxi, Dong, Xiaoting
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms catastrophic forgetting Computational modeling continual learning Continuing education Deep learning Deep reinforcement learning Distance learning Flight simulators Global Positioning System Heuristic algorithms Industrial robots Machine learning Memory tasks Neural networks Parameters Reinforcement learning Robot control Robot learning Robots Searching sequential multitask learning Synapses Task complexity Training Trajectory
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!