English

On the Optimal Amount of Experimentation in Sequential Decision Problems

Probability 2009-07-14 v1 Statistics Theory Statistics Theory
Authors: Dinah Rosenberg , Eilon Solan , Nicolas Vieille
View on arXiv ↗ PDF ↗

Abstract

We provide a tight bound on the amount of experimentation under the optimal strategy in sequential decision problems. We show the applicability of the result by providing a bound on the cut-off in a one-arm bandit problem.

Keywords

optimal stopping optimal experimental design risk theory

Cite

@article{arxiv.0907.2002,
  title  = {On the Optimal Amount of Experimentation in Sequential Decision Problems},
  author = {Dinah Rosenberg and Eilon Solan and Nicolas Vieille},
  journal= {arXiv preprint arXiv:0907.2002},
  year   = {2009}
}

Related papers

View all related →
Machine Learning · Computer Science
A Farewell to Arms: Sequential Reward Maximization on a Budget with a Giving Up Option
P Sharoff, Nishant A. Mehta, Ravi Ganti
2020-03-26
Machine Learning · Computer Science
Pure Exploration in Bandits with Linear Constraints
Emil Carlsson, Debabrota Basu, Fredrik D. Johansson, Devdatt Dubhashi
2024-01-26
Machine Learning · Computer Science
A Better Resource Allocation Algorithm with Semi-Bandit Feedback
Yuval Dagan, Koby Crammer
2018-03-29
Theoretical Economics · Economics
Approximate optimality and the risk/reward tradeoff in a class of bandit problems
Zengjing Chen, Larry G. Epstein, Guodong Zhang
2024-01-02
Methodology · Statistics
Optimal Conditional Inference in Adaptive Experiments
Jiafeng Chen, Isaiah Andrews
2026-01-21
Statistics Theory · Mathematics
Stochastic Bandit Based on Empirical Moments
Junya Honda, Akimichi Takemura
2013-03-29
Machine Learning · Computer Science
The Batch Complexity of Bandit Pure Exploration
Adrienne Tuynman, Rémy Degenne
2025-02-04
Machine Learning · Computer Science
Minimax Optimal Algorithms for Adversarial Bandit Problem with Multiple Plays
N. Mert Vural, Hakan Gokcesu, Kaan Gokcesu, Suleyman S. Kozat
2019-12-02
Data Structures and Algorithms · Computer Science
Sequential Design of Experiments via Linear Programming
Sudipto Guha, Kamesh Munagala
2013-06-19
Artificial Intelligence · Computer Science
Optimal Sensing via Multi-armed Bandit Relaxations in Mixed Observability Domains
Mikko Lauri, Risto Ritala
2016-03-16
Machine Learning · Computer Science
Continuous-Time Multi-Armed Bandits with Controlled Restarts
Semih Cayci, Atilla Eryilmaz, R. Srikant
2020-07-02
Statistics Theory · Mathematics
Optimal Best Arm Identification with Fixed Confidence
Aurélien Garivier, Emilie Kaufmann
2016-06-02
Statistics Theory · Mathematics
Refined bounds for randomized experimental design
Geovani Rizk, Igor Colin, Albert Thomas, Moez Draief
2021-01-01
Statistics Theory · Mathematics
Batched bandit problems
Vianney Perchet, Philippe Rigollet, Sylvain Chassang, Erik Snowberg
2016-03-30
Machine Learning · Computer Science
Query-Reward Tradeoffs in Multi-Armed Bandits
Nadav Merlis, Yonathan Efroni, Shie Mannor
2022-10-28
Machine Learning · Computer Science
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
Julian Katz-Samuels, Lalit Jain, Zohar Karnin, Kevin Jamieson
2020-06-23
Machine Learning · Computer Science
Active Learning with Safety Constraints
Romain Camilleri, Andrew Wagenmaker, Jamie Morgenstern, Lalit Jain +1
2022-06-23
Optimization and Control · Mathematics
Error bounds on the probabilistically optimal problem solving strategy
Frantisek Duris
2016-12-01
Information Theory · Computer Science
Sequential Multi-hypothesis Testing in Multi-armed Bandit Problems:An Approach for Asymptotic Optimality
Gayathri R Prabhu, Srikrishna Bhashyam, Aditya Gopalan, Rajesh Sundaresan
2022-06-13
Optimization and Control · Mathematics
An Asymptotically Optimal Strategy for Constrained Multi-armed Bandit Problems
Hyeong Soo Chang
2018-05-04
Machine Learning · Computer Science
Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits
Alexandra Carpentier, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos +2
2015-07-17
Machine Learning · Computer Science
Threshold-Based Optimal Arm Selection in Monotonic Bandits: Regret Lower Bounds and Algorithms
Chanakya Varude, Jay Chaudhary, Siddharth Kaushik, Prasanna Chaporkar
2025-09-03
Statistics Theory · Mathematics
Demonstration Experiments
Guido Imbens, Lorenzo Masoero, Alexander Rakhlin, Thomas S. Richardson +1
2026-03-10
Machine Learning · Computer Science
Replicable Bandits
Hossein Esfandiari, Alkis Kalavasis, Amin Karbasi, Andreas Krause +2
2023-02-16
Machine Learning · Computer Science
Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget
Jasmin Brandt, Viktor Bengs, Björn Haddenhorst, Eyke Hüllermeier
2022-10-17
R2 v1 2026-06-21T13:24:00.838Z