This content will become publicly available on January 1, 2024
Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency
- Award ID(s):
- 1906169
- NSF-PAR ID:
- 10436439
- Date Published:
- Journal Name:
- Annual Conference on Learning Theory (COLT)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
No document suggestions found
