Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution

Documenti analoghi

• Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning
  di: Huang, Changxin, et al.
  Pubblicazione: (2025)
• Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped Robots
  di: Liang, Junyang, et al.
  Pubblicazione: (2026)
• Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning
  di: Zeng, Runhao, et al.
  Pubblicazione: (2024)
• Foundational Policy Acquisition via Multitask Learning for Motor Skill Generation
  di: Yamamori, Satoshi, et al.
  Pubblicazione: (2023)
• Policy Learning from Large Vision-Language Model Feedback without Reward Modeling
  di: Luu, Tung M., et al.
  Pubblicazione: (2025)