tianjunz

HIR

TEMPERA

NovelD

MADE

agents

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

awesome-deep-rl

For deep RL and the future of AI.

azure-cli-cheatsheet

Azure CLI Cheatsheet

c-planning

DeepSpeedExamples

Example models using DeepSpeed

dreamerv2

Mastering Atari with Discrete World Models

GNNPapers

Must-read papers on graph neural networks (GNN)

guidance

A guidance language for controlling large language models.

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Learn_Prompting

marLo

Multi Agent Reinforcement Learning using MalmÖ

metaseq

Repo for external large-scale work

ml-agents

Unity Machine Learning Agents Toolkit

my-offlinerl

ort

Accelerate PyTorch models with ONNX Runtime

overcooked_ai

A benchmark environment for fully cooperative multi-agent performance.

poet

ML model training for edge devices

pymarl

Python Multi-Agent Reinforcement Learning framework

python

Official Python client library for kubernetes

pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

PyTorch-GAN

PyTorch implementations of Generative Adversarial Networks.

raft

random_name

softlearning

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.

tianjunz.github.io

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities