A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

COVID-19 Agent-based Simulator (Covasim): a model for exploring coronavirus dynamics and interventions

A suite of test scenarios for multi-agent reinforcement learning.

Bayesian optimisation library developped by Huawei Noah's Ark Lab

DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.

Multi-agent grid world stag hunt

A minimalist environment for decision-making in autonomous driving

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Submission for MAVEN: Multi-Agent Variational Exploration

[NeurIPS 2020] PyTorch implementation of "Learning Implicit Credit Assignment for Cooperative Muti-Agent Reinforcement Learning"

Learning Individual Intrinsic Reward in MARL

Official Code Release for Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Proximal Policy Optimization