New Study Examines Satisficing Regret Minimization in Bandits with Knapsacks
A new arXiv paper studies satisficing regret minimization in bandits with knapsacks, where a learner sequentially selects randomized policies, i.e., distributions.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-30 04:00 · arXiv stat.ML
Satisficing Regret Minimization in Bandits with Knapsacks