A differentiable physics engine and multibody dynamics library for control and robot learning.

A simple library for scaling up JAX programs

Scripts to recreate the D4RL datasets with Minari

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

A modular, easy to extend GFlowNet library

LLM training in simple, raw C/CUDA

Benchmarking RL generalization in an interpretable way.

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

Chromax is a breeding simulator based on JAX.

Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activelo…

A JAX-based simulator for autonomous driving research.

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

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

This repository contains implementations and illustrative code to accompany DeepMind publications

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Distributed Reinforcement Learning accelerated by Lightning Fabric

Sampling profiler for Python programs

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Some matplotlib plotting utilities (useful for papers)

The Official Code for Offline Model-based Adaptable Policy Learning

With Holoviews, your data visualizes itself.

Training and serving large-scale neural networks with auto parallelization.

A Reinforcement Learning Software Toolbox for Robotics

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

JAX and PZ RL envs + algorithms for swarms of CrazyFlies

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…

A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

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