Asymmetric self-play for automatic goal discovery in robotic manipulation
OpenAI OpenAI(OpenAI (United States)), Wojciech Zaremba(OpenAI (United States)), Arthur J Petron(OpenAI (United States)), Henrique Pondé de Oliveira Pinto, Tao Xu(University College of Islam Melaka), Matthias Plappert(OpenAI (United States)), Ilge Akkaya, Vineet Kosaraju(Stanford University), Ruben D'Sa(OpenAI (United States)), Raul Sampedro(OpenAI (United States)), Alex Paino, Hyeonwoo Noh(Korea Post), Lilian Weng(OpenAI (United States)), Qiming Yuan, Casey Chu(Stanford University), Peter Welinder(California Institute of Technology)
Cited by 21
Related Papers
Training language models to follow instructions with human feedback
|arXiv (Cornell University)|2022|4.3k
Learning dexterous in-hand manipulation
|The International Journal of Robotics Research|2019|1.6k
Evaluating Large Language Models Trained on Code
|arXiv (Cornell University)|2021|1.5k
Training Language Models to Follow Instructions with Human Feedback
|Unknown|2022|760
The Multidimensional Wisdom of Crowds
|CaltechAUTHORS (California Institute of Technology)|2010|735