Barrier Functions Inspired Reward Shaping for Reinforcement Learning

Documenti analoghi

• Scalable Learning of High-Dimensional Demonstrations with Composition of Linear Parameter Varying Dynamical Systems
  di: Agrawal, Shreenabh, et al.
  Pubblicazione: (2025)
• Energy-Efficient Quadruped Locomotion with Compliant Feet
  di: Pal, Pramod, et al.
  Pubblicazione: (2026)
• A Graph-Based Reinforcement Learning Approach with Frontier Potential Based Reward for Safe Cluttered Environment Exploration
  di: Calzolari, Gabriele, et al.
  Pubblicazione: (2025)
• GRoQ-LoCO: Generalist and Robot-agnostic Quadruped Locomotion Control using Offline Datasets
  di: PP, Narayanan, et al.
  Pubblicazione: (2025)
• Robotic Arm Manipulation with Inverse Reinforcement Learning & TD-MPC
  di: Hassan, Md Shoyib, et al.
  Pubblicazione: (2024)