Benjamin van Roy

Available identifiers

zbMath Open van-roy.benjaminWikidataQ88685704 ScholiaQ88685704MaRDI QIDQ399882

List of research outcomes

Publication	Date of Publication	Type
Reinforcement Learning, Bit by Bit	2023-12-19	Paper
Satisficing in Time-Sensitive Bandit Learning	2023-01-09	Paper
Learning to Optimize via Information-Directed Sampling	2020-10-05	Paper
https://portal.mardi4nfdi.de/entity/Q5214215	2020-02-07	Paper
A Tutorial on Thompson Sampling	2018-11-23	Paper
Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization	2017-09-22	Paper
Convergence of Min-Sum Message Passing for Quadratic Optimization	2017-08-08	Paper
Universal Reinforcement Learning	2017-07-27	Paper
Convergence of Min-Sum Message-Passing for Convex Optimization	2017-07-27	Paper
Gaussian-Dirichlet Posterior Dominance in Sequential Learning	2017-02-14	Paper
https://portal.mardi4nfdi.de/entity/Q2810878	2016-06-06	Paper
Adaptive Execution: Exploration and Learning of Price Impact	2016-03-22	Paper
Learning to Optimize via Posterior Sampling	2015-04-24	Paper
Directed Principal Component Analysis	2014-11-26	Paper
Learning a factor model via regularized PCA	2014-08-20	Paper
Resource Allocation via Message Passing	2012-07-28	Paper
Manipulation Robustness of Collaborative Filtering	2012-02-27	Paper
Dynamic Pricing with a Prior on Market Response	2011-11-24	Paper
Investment and Market Structure in Industries with Congestion	2011-11-24	Paper
Computational Methods for Oblivious Equilibrium	2011-11-17	Paper
Industry dynamics: foundations for models with an infinite number of firms	2011-10-28	Paper
Control of Diffusions via Linear Programming	2011-05-31	Paper
On regression-based stopping times	2010-10-15	Paper
A short proof of optimality for the MIN cache replacement algorithm	2010-01-29	Paper
A Nonparametric Approach to Multiproduct Pricing	2009-08-13	Paper
The Linear Programming Approach to Approximate Dynamic Programming	2009-07-09	Paper
Capacity of the Trapdoor Channel With Feedback	2009-02-24	Paper
Consensus Propagation	2008-12-21	Paper
Markov Perfect Industry Dynamics With Many Firms	2008-12-15	Paper
Performance Loss Bounds for Approximate Value Iteration with State Aggregation	2008-05-27	Paper
A Cost-Shaping Linear Program for Average-Cost Approximate Dynamic Programming with Performance Guarantees	2008-05-27	Paper
Strategic Execution in the Presence of an Uninformed Arbitrageur	2008-01-18	Paper
https://portal.mardi4nfdi.de/entity/Q3590801	2007-09-03	Paper
Convergence of the Min-Sum Algorithm for Convex Optimization	2007-05-29	Paper
A generalized Kalman filter for fixed point approximation and efficient temporal-difference learning	2007-01-18	Paper
https://portal.mardi4nfdi.de/entity/Q5477860	2006-06-29	Paper
https://portal.mardi4nfdi.de/entity/Q5201298	2006-04-18	Paper
On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming	2005-11-11	Paper
Algorithms and Models for the Web-Graph	2005-08-22	Paper
Decentralized decision-making in a large team with local information.	2003-07-30	Paper
https://portal.mardi4nfdi.de/entity/Q4547446	2002-08-21	Paper
An analysis of belief propagation on the turbo decoding graph with Gaussian densities	2002-08-04	Paper
On average versus discounted reward temporal-difference learning	2002-07-08	Paper
On the existence of fixed points for approximate value iteration and temporal-difference learning	2001-02-19	Paper
Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives	2000-10-17	Paper
Average cost temporal-difference learning	2000-02-28	Paper
An analysis of temporal-difference learning with function approximation	1999-05-06	Paper
Feature-based methods for large scale dynamic programming	1996-04-21	Paper

Research outcomes over time

Doctoral students

No records found.

Known relations from the MaRDI Knowledge Graph

Property	Value
MaRDI profile type	MaRDI person profile
instance of	human

This page was built for person: Benjamin van Roy