21 citations · 23 across the 3 of their papers we have counts for
3 papers
stat.ML2017★ 2 cited
Tree-Structured Boosting: Connections Between Gradient Boosted Stumps and Full Decision Trees
José Marcio Luna, Eric Eaton, Lyle H. Ungar +7
Additive models, such as produced by gradient boosting, and full interaction models, such as classification and regression trees (CART), are widely used algorithms that have been i…
cs.LG2017
Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer
David Isele, Mohammad Rostami, Eric Eaton
Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge…
cs.LG2015★ 21 cited
Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret
Haitham Bou Ammar, Rasul Tutunov, Eric Eaton
Lifelong reinforcement learning provides a promising framework for developing versatile agents that can accumulate knowledge over a lifetime of experience and rapidly learn new tas…