Jonathan Baxter

Available identifiers

zbMath Open baxter.jonathanMaRDI QIDQ1369060

List of research outcomes

Publication	Date of Publication	Type
Variance reduction techniques for gradient estimates in reinforcement learning	2011-10-12	Paper
Emmerald: a fast matrix–matrix multiply using Intel's SSE instructions	2003-02-04	Paper
https://portal.mardi4nfdi.de/entity/Q4533362	2002-10-13	Paper
https://portal.mardi4nfdi.de/entity/Q4533363	2002-10-10	Paper
Estimation and approximation bounds for gradient-based reinforcement learning	2002-07-04	Paper
Improved generalization through explicit optimization of margins	2001-02-05	Paper
Learning to play chess using temporal differences	2000-11-05	Paper
A Bayesian/information theoretic model of learning to learn via multiple task sampling	1997-01-01	Paper
https://portal.mardi4nfdi.de/entity/Q4852525	1995-11-29	Paper

Research outcomes over time

This page was built for person: Jonathan Baxter