Pages that link to "Item:Q4974829"
From MaRDI portal
The following pages link to A Structured Multiarmed Bandit Problem and the Greedy Policy (Q4974829):
Displaying 16 items.
- Response-adaptive designs for clinical trials: simultaneous learning from multiple patients (Q320737) (← links)
- An asymptotically optimal policy for finite support models in the multiarmed bandit problem (Q415624) (← links)
- Bayesian policy reuse (Q1689554) (← links)
- Multi-objective multi-armed bandit with lexicographically ordered and satisficing objectives (Q2051318) (← links)
- On Solving Finite State Multi-Armed Bandit Problem by Linear Programming (Q3360683) (← links)
- Polynomial-Time Algorithms for Multiple-Arm Identification with Full-Bandit Feedback (Q3386400) (← links)
- A Simple Distribution-Free Approach to the Max k-Armed Bandit Problem (Q3524258) (← links)
- Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback (Q4596721) (← links)
- The Nonstochastic Multiarmed Bandit Problem (Q4785631) (← links)
- Minimax Off-Policy Evaluation for Multi-Armed Bandits (Q5096994) (← links)
- Learning in Combinatorial Optimization: What and How to Explore (Q5144784) (← links)
- A linear response bandit problem (Q5168867) (← links)
- An incentive-compatible multi-armed bandit mechanism (Q5401464) (← links)
- Greedy Algorithm Almost Dominates in Smoothed Contextual Bandits (Q5890034) (← links)
- Multi-armed bandits with censored consumption of resources (Q6097147) (← links)
- A Bayesian two-armed bandit model (Q6574583) (← links)