Andrew_Y.__Ng
Algorithms for inverse reinforcement learning
Analysis, Eigenvectors and Stability
Convergence rates of the voting Gibbs classifier, with application to Bayesian feature selection
On feature selection: learning with exponentially many irrelevant features as training examples
On spectral clustering: Analysis and an algorithm
Pegasus: A policy search method for large mdps and pomdps
Policy invariance under reward transformations: Theory and application to reward shaping
Policy search via density estimation
Preventing "overfitting" of cross-validation data
Stable algorithms for link analysis