Kolar ML Lab
Open Menu
Close Menu
Home
Team
Publications
Contact
ESC
All Results
Searching...
No results found
Clear search
↑↓
Navigate
↵
Select
Powered by Hugo Blox
Pedro Cisneros Velarde
Personal website
Publications
One Policy is Enough: Parallel Exploration with a Single Policy is Minimax Optimal for Reward-Free Reinforcement Learning
Pedro Cisneros Velarde
,
Boxiang Lyu
,
Sanmi Koyejo
,
Mladen Kolar
International Conference on Artificial Intelligence and Statistics (AISTATS)
arXiv
URL
Cite
