Nature

LLMs augmented hierarchical reinforcement learning with action primitives for long-horizon manipulation tasks

Deep reinforcement learning methods have shown promising results in learning specific tasks, but struggle to cope with the challenges of long horizon manipulation tasks. As task complexity increases, ...
Nature

Railway infrastructure maintenance efficiency improvement using deep reinforcement learning integrated with digital twin based on track geometry and component defects

Demand for railway transportation is increasing every year. Based on the increasing load and speed of rolling stocks, railway maintenance is intensively required due to the rapid deterioration.