Non-Stochastic Control with Bandit Feedback Paula Gradu 1,3 John Hallman 1, 3 Elad Hazan
–Neural Information Processing Systems
For this problem, with either a known or unknown system, we give an efficient sublinear regret algorithm.
Neural Information Processing Systems
Oct-3-2025, 07:48:08 GMT
- Country:
- North America
- United States > New Jersey (0.04)
- Canada (0.04)
- Europe > Russia
- Central Federal District > Moscow Oblast > Moscow (0.04)
- Asia
- Russia (0.04)
- Middle East > Jordan (0.04)
- North America
- Technology: