Adversarial Linear Contextual Bandits
1RegretSchneider and Zimmert (2023)
Evaluation Results
| Method | Links | |
|---|---|---|
| Schneider and Zimmert (2023)Computation=poly(d, T), Simulator=no, Feedback=bandit2025.08 | 1 | |
| Neu and Valko (2014)Computation=poly(d, T) plus poly(d, T) oracle calls, Simulator=no, Feedback=semi-bandit2025.08 | 2 | |
| Liu et al. (2023)Computation=poly(d, K, T), Simulator=no, Feedback=bandit2025.08 | 2 | |
| Algorithm 1Computation=poly(d, T) plus poly(d, T) oracle calls, Simulator=no, Feedback=bandit2025.08 | 2 |