Software

JAXGenesis: A JAX Library for Training Deep Generative Models

JAX Genesis Logo

JAX Genesis: Implementations of different generative model architectures in the JAX framework using the Equinox JAX Library for neural network implementations.

Implemented Generative Model Architectures:

  • Generative Adversarial Networks
  • Variational AutoEncoders
  • Flow-Based Models
  • Energy-Based Models
  • Neural SDEs

OmnixRL: A JAX Library for Deep RL

OmnixRL Logo

OmnixRL: A comprehensive reinforcement learning library implemented in JAX, inspired by OpenAI's Spinning Up. This library provides a clean, modular implementation of popular RL algorithms with a focus on research experimentation and serves as a research framework for developing novel RL algorithms.

Implemented Deep Reinforcement Learning Algorithms:

  • Vanilla Policy Gradient (VPG)
  • Trust Region Policy Optimization (TRPO)
  • Proximal Policy Optimization (PPO)
  • Deep Deterministic Policy Gradient (DDPG)
  • Twin Delayed DDPG (TD3)
  • Soft Actor-Critic (SAC)

MLAlgorithmsKit: A Light-weight Machine Learning Library in Python

Implementation of standard ML Algorithms from scratch using Numpy and Pandas libraries.
Algorithms Implemented:

Linear Regression, Logistic Regression, Multi-Layered Perceptron, K-Means Clustering, KNN (K-Nearest Neighbors), Decision tree