16mins read Policy gradients Policy gradients is a family of algorithms for solving reinforcement learning problems by directly optimizing the policy in […]
16mins read Evolution strategies (ES) is an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on […]
14mins read Weighted sampling from a list-like collection is an important activity in many applications. Weighted sampling involves selecting samples randomly from […]
39mins read Introduction Recurrent Neural Networks (or more precisely LSTM/GRU) have been found to be very effective in solving complex sequence-related problems […]
16mins read Introduction Eigenvectors and eigenvalues have many important applications in computer vision and machine learning in general. Well-known examples are PCA (Principal […]
8mins read Introduction There are several methods to calculate gradients in computer programs: (1) Manual differentiation; (2) Symbolic differentiation; (3) Finite differences […]