TBC-HRL: A Bio-Inspired Framework for Stable and Interpretable Hierarchical Reinforcement Learning

Hierarchical Reinforcement Learning (HRL) is effective for long-horizon and sparse-reward tasks by decomposing complex decision processes, but its real-world application remains limited due to instability between levels, inefficient subgoal scheduling, delayed responses, and poor interpretability. T...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Zepei Li, Yuhan Shan, Hongwei Mo
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	MDPI AG 2025-10-01
Σειρά:	Biomimetics
Θέματα:	hierarchical reinforcement learning bionic neural circuits timed subgoal scheduling liquid time-constant network neurodynamic control robot learning
Διαθέσιμο Online:	https://www.mdpi.com/2313-7673/10/11/715
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!