Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Documenti analoghi

• DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
  di: Mu, Tongzhou, et al.
  Pubblicazione: (2024)
• Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
  di: Escoriza, Adrià López, et al.
  Pubblicazione: (2025)
• Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
  di: Wang, Yiqi, et al.
  Pubblicazione: (2025)
• When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?
  di: Mu, Tongzhou, et al.
  Pubblicazione: (2024)
• Sensory-Motor Control with Large Language Models via Iterative Policy Refinement
  di: Carvalho, Jônata Tyska, et al.
  Pubblicazione: (2025)