PPO-Algorithms

Spark library for generalized K-Means clustering. Supports general Bregman divergences. Suitable for clustering probabilistic data, time series data, high dimensional data, and very large data.

Maximum entropy and minimum divergence models in Python

Stabilizing an Inverted Pendulum on a cart using Deep Reinforcement Learning

? ? Fast Python implementation of various Kullback-Leibler divergences for 1D and 2D parametric distributions. Also provides optimized code for kl-UCB indexes

Implement RL algorithms in PyTorch and test on Gym environments.

Non-Negative Matrix Factorization for Gene Expression Clustering

Basic GANs with variety of loss functions as an exercise for my Thesis with Prof. Randy Paffenroth. KL, Reverse-KL, JS and Wasserstein GAN.

This repository contains a re-implementation of the Proximal Policy Optimization (PPO) algorithm, originally sourced from Stable-Baselines3.

Simple Muesli RL algorithm implementation (PyTorch)

Contains Expert Trajectories for various Gym Environments used for State Only Imitation Learning