Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

GPU-accelerated NeuroEvolution of Augmenting Topologies (NEAT)

MetaDE is a GPU-accelerated evolutionary framework that optimizes Differential Evolution (DE) strategies via meta-level evolution. Supporting both JAX and PyTorch, it dynamically adapts mutation and crossover strategies for efficient large-scale black-box optimization.

a modular reinforcement learning library with JAX agents

GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA.

Reinforcement learning in pure JAX.

Relentlessly learning, persistently failing, but never surrendering.

[ICML 2024] Official environments and JAX-implementations for "Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments"

Procedural Environment Generation for Accelerated Multi-Agent Reinforcement Learning

🚀 Benchmark GPU and CPU performance accurately across diverse hardware using PyTorch and TensorFlow, generating metrics and dashboards for optimization.