Montreal Robotics and Embodied AI Lab (REAL)

DeepRLInTheWorld

From search engines, to science, to robotics, this reposity is meant to showcase the use of reinforcement learning in the world..

iv_rl

IV-RL - Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation

ctrl-sim

Official repository for "CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning"

one4all

An end-to-end fully parametric method for image-goal navigation that leverages self-supervised and manifold learning to replace the topological graph with a geodesic regressor.

montrealrobotics.github.io

robo-gym-robot-servers

Repository containing Robot Servers ROS packages

harmonic-filter

Code for the Harmonic Exponential Filter

panda-gym

Set of robotic environments based on PyBullet physics engine and gymnasium.

REAL_lab_info

Information about our lab, the repositories that we use and how we work.

risk_aware_exploration

test-of-time-workshop

ur_kinematics

bullet3

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

cleanrl

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

ctrlsim

droid

Distributed Robot Interaction Dataset.

fairo

A modular embodied agent architecture and platform for building embodied agents

hef

HEF Website

o4a

O4A Website

octo

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

ood_slam

puppersim

Simulation for DJI Pupper v2 robot

robo-gym

An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.

robotiq

Robotiq packages (http://wiki.ros.org/robotiq)

robotiq_grippers

ROS package for Robotiq Gripper 85 and Hand-e

roboverse

A set of environments utilizing pybullet for simulation of robotic manipulation tasks.

ros_robotiq_urcap_control

Control our robotiq grippers (2F-85 and Hand-E) from ROS thru the Robotiq URCap on the e-series.

safety-gymnasium

Safety-Gymnasium is a highly scalable and customizable safe reinforcement learning environment library.

SimplerEnv

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)

website-assets