The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Code for Discovering Preference Optimization Algorithms with and for Large Language Models

Accelerated minigrid environments with JAX

Seamlessly integrate LLMs as Python functions

JAX implementation of the Mistral 7b v0.1 model

Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]

flexible meta-learning in jax

Optax implementation of shrink and perturb (Ash & Adams, 2020).

Machine Learning Engineering Open Book

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

This is the offcicial repo of the pygame modelling course for collective systems workshop 2022 Berlin

Multi-Agent Reinforcement Learning of Crowd Simulation in GPU (PyTorch)

🧠🗼

A public python implementation of the DeepHyperNEAT system for evolving neural networks. Developed by Felix Sosa and Kenneth Stanley. See paper here: https://eplex.cs.ucf.edu/papers/sosa_ugrad_repo…

[NeurIPS DBT 2021] HPO-B

[JMLR-2024] PyPop7: A Pure-Python Library for POPulation-based Black-Box Optimization (BBO), especially their *Large-Scale* versions/variants (-> evolutionary algorithms/swarm-based optimizers/patt…

Package for working with hypernetworks in PyTorch.

GPT implementation in Flax

Easy Hypernetworks in Pytorch and Jax

Research workflows made easy, locally and in the Cloud.

Code and links for over 25,000 trained Atari agents

Everything you want to know about Google Cloud TPU

JAX - A curated list of resources https://github.com/google/jax

A Slurm dashboard for the terminal.

Implementations and checkpoints for ResNet, Wide ResNet, ResNeXt, ResNet-D, and ResNeSt in JAX (Flax).

Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights on all environments.