PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

Natural Gradient Boosting for Probabilistic Prediction

About A collection of AWESOME things about information geometry Topics

Gaussian Process package based on data augmentation, sparsity and natural gradients

TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".

Natural Gradient, Variational Inference

Code for the paper "Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift"

Actor Critic using Kronecker-Factored Trust Region

(CEC2022) Fast Moving Natural Evolution Strategy for High-Dimensional Problems

High-performance implementations of several reinforcement learning algorithms and some commonly used benchmark problems (Matlab & C++)

Simple Experiments mainly on Machine Learning

Matrix-multiplication-only KFAC; Code for ICML 2023 paper on Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning

(CEC2023 Tutorial) Foundations and Recent Advances on Natural Evolution Strategies

(EvoApps2022) "Towards a Principled Learning Rate Adaptation for Natural Evolution Strategies"

Approximate Natural Gradient Descent with precision weighted predictive coding

My Master's Thesis on Variational Optimization of Neural Networks written at the Technical University of Denmark

Project definition and implementations for Convex Optimization Course

Faster large mini-batch distributed training w/o. squeezing devices