atavakol

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Gymnasium

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

cleanrl

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

brax

Massively parallel rigidbody physics simulation on accelerator hardware.

rl

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

jraph

A Graph Neural Network Library in Jax

ravens

Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.

mujoco-worldgen

Automatic object XML generation for Mujoco

stable-baselines3-contrib

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

minihack

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

dqn_zoo

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

phyre

PHYRE is a benchmark for physical reasoning.

lab2d

A customisable 2D platform for agent-based AI research

url_benchmark

atari-model-zoo

A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release that enables easy visualization and analysis of models, and comparison across training algorithms.

Shimmy

An API conversion tool for popular external reinforcement learning environments

ppo-pytorch

Proximal Policy Optimization(PPO) with Intrinsic Curiosity Module(ICM)

exorl

ExORL: Exploratory Data for Offline Reinforcement Learning

animal-ai

Animal-AI 3

offworld-gym

OffWorld Gym: Open-Access Physical Robotics Environment for Real-World Reinforcement Learning Benchmark and Research

ppo-ewma

Code for the paper "Batch size invariance for policy optimization"

pink-noise-rl

beta-nll

beta-NLL introduced in our paper "On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks" ICLR 2022

logrl

Logarithmic Reinforcement Learning

qreps

LoCA2

orchestrated-value-mapping

Orchestrated Value Mapping

jax-tutorial

JAX Tutorial for Autonomous Learning Group Retreat