机器人学arXiv 20252025年5月

Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids

OpenAI, Marcin Andrychowicz, Bowen Baker, Maciek Chociej, Rafal Jozefowicz, Bob McGrew, Jakub Pachocki, Arthur Petron, Matthias Plappert, Glenn Powell, Alex Ray, Jonas Schneider, Szymon Sidor, Josh Tobin, Peter Welinder, Lilian Weng, Wojciech ZarembaGoogle DeepMind

摘要

Sim-to-real reinforcement learning for achieving vision-based dexterous manipulation on humanoid robots.

sim-to-realreinforcement learningdexterous manipulation