3- https://doi.org/10.1016/j.biosystems.2015.06.009
Overtaking method based on sand-sifter mechanism: Why do optimistic value functions find optimal solutions in multi-armed bandit problems?
- Jul 10, 2015
- Biosystems
- Kento Ochi +1 more
Abstract
Overtaking method based on sand-sifter mechanism: Why do optimistic value functions find optimal solutions in multi-armed bandit problems?
- # Multi-armed Bandit
- # UCB Algorithm
- # Value Function
- # Learning Agent
- # Low Regret
- # Search Problem
- # Uncertain Environment
- # High Regret
- # Time Step
- # Function Of Arms
