The following pages link to A penalized bandit algorithm (Q1039016):
Displaying 6 items.
- On ergodic two-armed bandits (Q417067) (← links)
- Convergence in models with bounded expected relative hazard rates (Q472194) (← links)
- Stochastic approximation of quasi-stationary distributions on compact spaces and applications (Q1617129) (← links)
- Nonlinear randomized urn models: a stochastic approximation viewpoint (Q2274219) (← links)
- Regret bounds for Narendra-Shapiro bandit algorithms (Q5086451) (← links)
- Some simple but challenging Markov processes (Q5963357) (← links)