Covariance Matrix Adaptation Evolution Strategy (CMA-ES)

Modern C++ port of the original implementation of the Nelder-Mead algorithm to minimize a scalar function of several variables.

"Probabilistic Machine Learning" - a book series by Kevin Murphy

GPU C++ Monte Carlo Radiation Simulation with NVIDIA Thrust

Sequential, multithreaded and parallel implementation of Monte Carlo method with the use of modern C++ and OpenMP/OpenMPI (CPU) and CUDA (GPU).

choosing FFT library...

A DQN agent that optimally hedges an options portfolio.

An implementation of Performer, a linear attention-based transformer, in Pytorch

code for "Optimal Stopping via Randomized Neural Networks"

Deep Optimal Stopping Project

A Program to calculate the price of American put or call option with Least Square Monte Carlo

Pricing American style option by estimating optimal stopping time using deep learning

Normally Distributed Random Number Generator Benchmark

Cython interface for the interior point optimzer IPOPT

Automatic Differentiation Package for MATLAB

library for nonlinear optimization, wrapping many algorithms for global and local, constrained or unconstrained, optimization

Guide for building custom op for TensorFlow

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

COIN-OR Branch-and-Cut solver

Implementation of the Deep Deterministic Policy Gradient (DDPG) using PyTorch

Deep Hedging Demo - An Example of Using Machine Learning for Derivative Pricing.

PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).

Reinforcement Learning for Portfolio Management

Parallel implementation of DDPG

Personal Collection of Reinforcement Learning Algorithms. So far: Parallelized DDPG,...

Parallel DDPG Actor Critic architecture on Unity Tennis environment

Distributed Tensorflow Implementation of Asynchronous DDPG

An asynchronous DDPG algorithm with multiple Actor-Critic pairs. Fourth place in NeurIPS 2018: AI for Prosthetics Challenge.

A deep reinforcement learning model for portfolio management. For more info, check