Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Matplotlib styles for scientific plotting

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)

Machine learning glossary

An offline deep reinforcement learning library

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

Some Conferences' accepted paper lists (including AI, ML, Robotic)

Reinforcement Learning Environments for Omniverse Isaac Gym

High throughput synchronous and asynchronous reinforcement learning

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.

Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab

An extension of the PyMARL codebase that includes additional algorithms and environment support

Pytorch Implementation of Reinforcement Learning Algorithms ( Soft Actor Critic(SAC)/ DDPG / TD3 /DQN / A2C/ PPO / TRPO)

Additional environments compatible with OpenAI gym

This package provides a framework to automatically perform grasp tests on an arbitrary object model of choice.

Wrappers and utilities for Nvidia IsaacGym

Brain Agent for Large-Scale and Multi-Task Agent Learning

Public Source Seeking Repository

BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with Isaac Gym

Additional environments compatible with OpenAI gym

High throughput asynchronous reinforcement learning

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.