alexanderdurr

DRNets-Nature-Machine-Intelligence

pybullet_robot

A generel Python interface class for robot simulations using PyBullet. An implementation of Franka Emika Panda robot interface provided as example.

aml_install

Install scripts for the Advanced Manipulation Learning (AML) framework.

ARM

Attention-driven Robot Manipulation (ARM) which includes Q-attention

covariance_ellipsoid_python

Convenience functions to compute covariance of data and get its ellipsoid representation. Also has convenience tools for visualising covariance ellipse/ellipsoid for 2D/3D data.

disentanglement_lib

disentanglement_lib is an open-source library for research on learning disentangled representations.

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

franka_panda_description

Franka Emika Panda robot description, modified for providing gazebo simulation. Also includes more accurate dynamics values for KDL dynamics parameter estimations.

LanguagePolicies

Supplemental code for our NeurIPS 2020 paper.

lime

Lime: Explaining the predictions of any machine learning classifier

mujoco_panda

Model definitions and Python API for controlling a Franka Emika Panda robot in the mujoco physics simulator.

multiplayer-alphazero

PyTorch AlphaZero implementation with multiplayer support [NeurIPS 2019 Deep Reinforcement Learning Workshop]

muzero

A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each other, and investigate reliability of learned MuZero MDP models.

NeSyConceptLearner

neural-symbolic-machines

Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.

neuro-symbolic-ai-soc

Neuro-Symbolic Visual Question Answering on Sort-of-CLEVR using PyTorch

NSCL-PyTorch-Release

PyTorch implementation for the Neuro-Symbolic Concept Learner (NS-CL).

OMG-Planner

An Optimization-based Motion and Grasp Planner

panda-autograsp

An autonomous grasping solution for the Emika Franka Panda robot.

piarm

PyRep

A toolkit for robot learning research.

PyTorch-GAN

PyTorch implementations of Generative Adversarial Networks.

reversible_dmp

Testing a reversible version of Dynamic Movement Primitives

RLzoo

A Comprehensive Reinforcement Learning Zoo for Simple Usage 🚀

ros_docker

Docker images for ROS master, bridge and nodes

ros_noetic_docker_env

A custom ROS Noetic docker environment for personal use and research experiments

rt-kernel-docker-builder

build and setup RT kernel for the ROS2 testing

warehouse_ros_mongo

Implementation of warehouse_ros using MongoDB

warp-drive

Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU

wasp-poster

Latex WASP poster template