cvoelcker

reinforcement-learning-material-ws-2018

This repository collects supplementary material to study reinforcement learning with a focus on topics covered by the TU Darmstadt IAS lecture on reinforcement learning.

DeepNotebooks

DeepNotebooks is an automated statistical analysis tool build on top of SPNs. They are currently being developed by Claas Völcker at the ML group at TU Darmstadt.

Awesome-CV

:page_facing_up: Awesome CV is LaTeX template for your outstanding job application

genesis

Official PyTorch implementation of "GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations"

master_experiments

variational_autoencoder_talk

A talk I've given on variational autoencoders. My first ever lecture

hero-manager

A django application to manage your rpg gaming group

IsaacGymEnvs

Isaac Gym Reinforcement Learning Environments

MONet

An implementation of the MONet model for unsupervised scene decomposition in PyTorch

PyConfigMaker

A yaml parser which automatically writes and reads config files to easily usable python namedtuples:w

sequential_inference

A repository for sequence models build on amortized variational inference in pytorch

alm

Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective

auto-postcard

Generate postcard texts automatically

auto_yolo

TensorFlow implementation of Spatially Invariant Attend, Infer, Repeat (SPAIR).

blog

This is my blog currently accessible under https://cvoelcker.de

dmc2gym

OpenAI Gym wrapper for the DeepMind Control Suite

exPy

Experimentation setup and results management framework for machine learning approaches

input-inference-for-control

Input Inference for Control (i2c), a control-as-inference framework for optimal control

jax_modules

Collection of useful jax snippets and modules to build more complex differentiable code

mbrl-lib

Library for Model Based RL

PyTorchRunner

A leightweight framework for experiment handling in pytorch

SPFlow

Sum Product Flow: An Easy and Extensible Library for Sum-Product Networks

spn-pytorch-experiments

Experiments on the integration of Sum-Product Networks into Deep Neural Networks.

spr

Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"

sqair

Implementation of Sequential Attend, Infer, Repeat (SQAIR)

STOVE

Structured Object-Aware Physics Prediction for Video Modeling and Planning

STOVE-1

Anonymous ICLR 2020 Submission: Structured Object-Aware Physics Prediction for Video Modelling and Planning

uoft-cs-robotics.github.io

University of Toronto cs robotics group

vagram_quadratic

variational-smc

Reference implementation of variational sequential Monte Carlo proposed by Naesseth et al. "Variational Sequential Monte Carlo" (2018)