FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control

Documenti analoghi

• Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
  di: Seo, Younggyo, et al.
  Pubblicazione: (2025)
• Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
  di: Seo, Younggyo, et al.
  Pubblicazione: (2024)
• HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation
  di: Sferrazza, Carmelo, et al.
  Pubblicazione: (2024)
• RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains
  di: Zhang, Yuanhang, et al.
  Pubblicazione: (2026)
• Body Transformer: Leveraging Robot Embodiment for Policy Learning
  di: Sferrazza, Carmelo, et al.
  Pubblicazione: (2024)