Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

OpenCL backend for CuPy

RUDDER for ATARI games with delayed rewards in OpenAI Baselines package

Models and examples built with TensorFlow

Differentiable Neural Computers (Testing the generalization of a sequence of sums)

Caffe: a fast open framework for deep learning.

Multiagent Cooperation and Competition with Deep Reinforcement Learning

Caffe: a Fast framework for deep learning. For the most recent version checkout the dev branch. For the latest stable release checkout the master branch.

Caffe

Deep Q learning agent playing 2048!

An implementation of Deep Q-Network using Caffe

The General Game Playing Base Package

The C++ Network Library Project -- cross-platform, standards compliant networking library.