PrefMMT: Modeling Human Preferences in Preference-based Reinforcement Learning with Multimodal Transformers

Documenti analoghi

• Personalization in Human-Robot Interaction through Preference-based Action Representation Learning
  di: Wang, Ruiqi, et al.
  Pubblicazione: (2024)
• PrefCLM: Enhancing Preference-based Reinforcement Learning with Crowdsourced Large Language Models
  di: Wang, Ruiqi, et al.
  Pubblicazione: (2024)
• PrefMoE: Robust Preference Modeling with Mixture-of-Experts Reward Learning
  di: Yuan, Ziqin, et al.
  Pubblicazione: (2026)
• PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models
  di: Wang, Ruiqi, et al.
  Pubblicazione: (2025)
• Adaptive Task Allocation in Multi-Human Multi-Robot Teams under Team Heterogeneity and Dynamic Information Uncertainty
  di: Yuan, Ziqin, et al.
  Pubblicazione: (2024)