108 citations · 175 across the 4 of their papers we have counts for
5 papers
PureTD: Reinforcement Learning for Backgammon Money Games with No Evaluation-time Search
Alexander L. Strehl
We revisit Tesauro's TD-Gammon for backgammon money games in the setting of no evaluation-time search. Both checker play and cube action (use of the doubling cube) are learned from…
Conditional Probability Tree Estimation Analysis and Algorithms
Alina Beygelzimer, John Langford, Yuri Lifshits +2
We consider the problem of estimating the conditional probability of a label in time O(log n), where n is the number of possible labels. We analyze a natural reduction of this prob…
Incremental Model-based Learners With Formal Learning-Time Guarantees
Alexander L. Strehl, Lihong Li, Michael L. Littman
Model-based learning algorithms have been shown to use experience efficiently when learning to solve Markov Decision Processes (MDPs) with finite state and action spaces. However,…
Learning from Logged Implicit Exploration Data
Alex Strehl, John Langford, Sham Kakade +1
We provide a sound and consistent foundation for the use of \emph{nonrandom} exploration data in "contextual bandit" or "partially labeled" settings where only the value of a chose…
Conditional Probability Tree Estimation Analysis and Algorithms
Alina Beygelzimer, John Langford, Yuri Lifshits +2
We consider the problem of estimating the conditional probability of a label in time , where is the number of possible labels. We analyze a natural reduction of this…