Nando de Freitas

Publications by Year

Research Areas

Reinforcement Learning in Robotics, Machine Learning and Algorithms, Gaussian Processes and Bayesian Inference, Advanced Bandit Algorithms Research, Domain Adaptation and Few-Shot Learning

Most-Cited Works

• → Sequential Monte Carlo Methods in Practice(2001)7,353 cited
• → Taking the Human Out of the Loop: A Review of Bayesian Optimization(2015)5,585 cited
• → An Introduction to MCMC for Machine Learning(2003)2,386 cited
• → A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning(2010)2,138 cited
• → Dueling Network Architectures for Deep Reinforcement Learning(2015)1,813 cited
• The Unscented Particle Filter(2000)
• → An Introduction to Sequential Monte Carlo Methods(2001)1,128 cited
• → A Boosted Particle Filter: Multitarget Detection and Tracking(2004)1,029 cited
• → Learning to Communicate with Deep Multi-Agent Reinforcement Learning(2016)867 cited
• → Predicting Parameters in Deep Learning(2013)704 cited