Pages that link to "Item:Q1614793"
From MaRDI portal
The following pages link to Optimal learning and experimentation in bandit problems. (Q1614793):
Displayed 19 items.
- A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems (Q949395) (← links)
- Online regret bounds for Markov decision processes with deterministic transitions (Q982638) (← links)
- Response adaptive designs that incorporate switching costs and constraints (Q997275) (← links)
- A Bayesian analysis of human decision-making on bandit problems (Q1042313) (← links)
- Optimal stopping for Brownian motion with applications to sequential analysis and option pricing (Q1763432) (← links)
- Gittins' theorem under uncertainty (Q2076662) (← links)
- The multi-armed bandit problem: an efficient nonparametric solution (Q2176624) (← links)
- Optimal learning with non-Gaussian rewards (Q2806349) (← links)
- Variance Regularization in Sequential Bayesian Optimization (Q3387910) (← links)
- Online Regret Bounds for Markov Decision Processes with Deterministic Transitions (Q3529915) (← links)
- INDEXABILITY OF BANDIT PROBLEMS WITH RESPONSE DELAYS (Q3585147) (← links)
- On Incomplete Learning and Certainty-Equivalence Control (Q4971399) (← links)
- The Local Time Method for Targeting and Selection (Q4971570) (← links)
- Optimistic Gittins Indices (Q5060515) (← links)
- Algorithms for recursive delegation (Q5145458) (← links)
- ON THE IDENTIFICATION AND MITIGATION OF WEAKNESSES IN THE KNOWLEDGE GRADIENT POLICY FOR MULTI-ARMED BANDITS (Q5358114) (← links)
- Corrected random walk approximations to free boundary problems in optimal stopping (Q5426468) (← links)
- Sequential Generalized Likelihood Ratios and Adaptive Treatment Allocation for Optimal Sequential Selection (Q5478885) (← links)
- Optimal anytime regret with two experts (Q6062702) (← links)