regret bounds | Sciweavers

ICML
2010
IEEE

204views Machine Learning» more ICML 2010»

Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design

13 years 12 months ago

Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multiarmed bandit problem, where the payoff function is ...

Niranjan Srinivas, Andreas Krause, Sham Kakade, Ma...

claim paper

Read More »

27
posts

with
8473
views

1430profile views Browse My Posts »

olethrosPostdoctoral

EPFL

Homepage lia.epfl.ch

Bayesian Reinforcement Learning | Complexity Analysis | Decision Theory | Intrusion Detection | Learning In Games | Machine Learning | Partially Observable Stochastic Games | POMDPs | Regret Bounds | Reinforcement Learning | Stochastic Optimization |

posted by olethros Mar 14 2010

Read More »

Sciweavers

Bayesian Reinforcement Learning | Complexity Analysis | Decision Theory | Intrusion Detection | Learning In Games | Machine Learning | Partially Observable Stochastic Games | POMDPs | Regret Bounds | Reinforcement Learning | Stochastic Optimization |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers