Open AccessJournal Article
Counterfactual reasoning and learning systems: the example of computational advertising
Léon Bottou,Jonas Peters,Joaquin Quiñonero-Candela,Denis X. Charles,D. Max Chickering,Elon Portugaly,Dipankar Ray,Patrice Y. Simard,Ed Snelson +8 more
Reads0
Chats0
TLDR
This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system and allow both humans and algorithms to select the changes that would have improved the system performance.Abstract:
This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system. Such predictions allow both humans and algorithms to select the changes that would have improved the system performance. This work is illustrated by experiments on the ad placement system associated with the Bing search engine.read more
Citations
More filters
Proceedings Article
On Open-Universe Causal Reasoning.
Duligur Ibeling,Thomas Icard +1 more
TL;DR: In this article, structural equation models and simulation models are extended to infinite variable spaces, which enables a semantics for conditionals founded on a calculus of intervention, and axiomatization of causal reasoning for rich, expressive generative models.
Optimal algorithms for experts and mixtures of Gaussians
TL;DR: This thesis makes contributions to two problems in learning theory: prediction with expert advice and learning mixtures of Gaussians and distribution learning, which is a fundamental task in statistics that has been studied for over a century.
Posted Content
Overfitting and Optimization in Offline Policy Learning.
TL;DR: The phenomenon of ``bandit overfitting'' is described, in which an algorithm overfits based on the actions observed in the dataset, and it is shown that it affects policy optimization but not Q-learning.
Posted Content
Debiased Off-Policy Evaluation for Recommendation Systems
TL;DR: A method for predicting the performance of reinforcement learning and bandit algorithms, given historical data that may have been generated by a different algorithm, and it is found that the method produces smaller mean squared errors than state-of-the-art methods.
Posted Content
Gradient Regularized Budgeted Boosting.
TL;DR: This paper proposes an algorithm that leverages the unlabeled data (through Laplace smoothing) and learns classifiers with budget constraints, which is, to the authors' knowledge, the first algorithm for semi-supervised budgeted learning.
References
More filters
Book
Reinforcement Learning: An Introduction
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
MonographDOI
Causality: models, reasoning, and inference
TL;DR: The art and science of cause and effect have been studied in the social sciences for a long time as mentioned in this paper, see, e.g., the theory of inferred causation, causal diagrams and the identification of causal effects.
Journal ArticleDOI
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
TL;DR: This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units that are shown to make weight adjustments in a direction that lies along the gradient of expected reinforcement in both immediate-reinforcement tasks and certain limited forms of delayed-reInforcement tasks, and they do this without explicitly computing gradient estimates.
Book
Introduction to Reinforcement Learning
TL;DR: In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning.