Dohyeong Kim, Hyeokjin Kwon, Junseok Kim, Gunmin Lee, and Songhwai Oh, "Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach," arXiv preprint arXiv:2409.15755, 2024.
Paper link: arxiv.org/abs/...
(The voice was generated by OpenAI TTS API.)
Негізгі бет Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective RL Approach
Пікірлер: 1