The following pages link to Algorithmic Learning Theory (Q5464503):
Displaying 6 items.
- Nonstochastic bandits: Countable decision set, unbounded costs and reactive environments (Q924170) (← links)
- On the possibility of learning in reactive environments with arbitrary dependence (Q950202) (← links)
- Learning Volatility of Discrete Time Series Using Prediction with Expert Advice (Q3646115) (← links)
- The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses (Q3648741) (← links)
- Prediction with Expert Advice under Discounted Loss (Q4930703) (← links)
- Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization (Q6183761) (← links)