Two-Layered Reward Reinforcement Learning in Humanoid Robot Motion Tracking
In reinforcement learning (RL), reward function design is critical to the learning efficiency and final performance of agents. However, in complex tasks such as humanoid motion tracking, traditional static weighted reward functions struggle to adapt to shifting learning priorities across training st...
Gardado en:
| Principais autores: | , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado: |
MDPI AG
2025-10-01
|
| Series: | Mathematics |
| Assuntos: | |
| Acceso en liña: | https://www.mdpi.com/2227-7390/13/21/3445 |
| Tags: |
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
|