Jakob Thumm's repositories
safe_rl_manipulators
Verifiably Safe Deep Reinforcement Learning for Robotic Manipulationin Human Environments
safety-intervention-reduction
The code for the articel "Reducing Safety Interventions in Provably Safe Reinforcement Learning".
jakobthumm.github.io
Personal Website of Jakob Thumm
feasible-actor-critic
Code for paper Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety.
safe-control-gym
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
TUM-CONCERT-Docker
Docker files for CONCERT Integration of TUM
concert_planning
ROS package for planning manipulation trajectories with MoveIt
depthimage_to_laserscan
Converts a depth image to a laser scan for use with navigation and localization.
dreamerv3
Mastering Diverse Domains through World Models
human-gazebo
Human animation replay and motion capture in gazebo
kalman-cpp
Basic Kalman filter implementation in C++ using Eigen
libfranka-SaRA
C++ library for Franka research robots
magicalsupplies
Public webpage I created for a murder mystery night.
magicsupplies
This is a website I created for a murder mystery party.
n-dim-reach-env
A simple reach environment with variable dimensionality.
OpenKF
This is an open source Kalman filter C++ library based on Eigen3 library for matrix operations. The library has generic template based classes for most of Kalman filter variants including: (1) Kalman Filter, (2) Extended Kalman Filter, (3) Unscented Kalman Filter, and (4) Square-root UKF..
rl-baselines3-zoo
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
rlpyt
Reinforcement Learning in PyTorch
safety-gym
Tools for accelerating safe exploration research.
scod-regression
A functorch-accelerated framework for efficient neural network uncertainty quantification with SCOD
spinningup
An educational resource to help anyone learn deep reinforcement learning.
stable-baselines3-contrib
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
STAP
Official repository for "STAP: Sequencing Task-Agnostic Policies," presented at ICRA 2023.