Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
JMLR
2012
9 years 8 months ago
Contextual Bandit Learning with Predictable Rewards
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
Alekh Agarwal, Miroslav Dudík, Satyen Kale,...
AMAI
2011
Springer
10 years 5 months ago
Multi-armed bandits with episode context
A multi-armed bandit episode consists of n trials, each allowing selection of one of K arms, resulting in payoff from a distribution over [0, 1] associated with that arm. We assum...
Christopher D. Rosin
AGI
2011
10 years 9 months ago
Reinforcement Learning and the Bayesian Control Rule
We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
Pedro Alejandro Ortega, Daniel Alexander Braun, Si...
JMLR
2010
103views more  JMLR 2010»
11 years 10 days ago
Regret Bounds and Minimax Policies under Partial Monitoring
This work deals with four classical prediction settings, namely full information, bandit, label efficient and bandit label efficient as well as four different notions of regret: p...
Jean-Yves Audibert, Sébastien Bubeck
CORR
2008
Springer
136views Education» more  CORR 2008»
11 years 5 months ago
Multi-Armed Bandits in Metric Spaces
In a multi-armed bandit problem, an online algorithm chooses from a set of strategies in a sequence of n trials so as to maximize the total payoff of the chosen strategies. While ...
Robert Kleinberg, Aleksandrs Slivkins, Eli Upfal
SDM
2007
SIAM
167views Data Mining» more  SDM 2007»
11 years 7 months ago
Bandits for Taxonomies: A Model-based Approach
We consider a novel problem of learning an optimal matching, in an online fashion, between two feature spaces that are organized as taxonomies. We formulate this as a multi-armed ...
Sandeep Pandey, Deepak Agarwal, Deepayan Chakrabar...
books