onnoeberhard

deepspeech-paper

deepspeech-transfer

A TensorFlow implementation of Baidu's DeepSpeech architecture

oscillator-gym

A flexible harmonic oscillator environment for OpenAI Gym

coding-challenge-retreat

actio

A very amitious Android project, unfinished

agnes1

My first ever project (2007)

ajents

Reinforcement Learning in JAX

aml

My Notes on the book "Learning from Data" by Yaser S. Abu-Mostafa, Malik Magdon-Ismail and Hsuan-Tien Lin

avr-projects

Old projects of mine for ATmega8

bachelorprojekt

clock-2.0

An Android clock and timer app

colorednoise

Python package to generate Gaussian (1/f)**beta noise (e.g. pink noise)

d4rl

A benchmark for offline reinforcement learning.

deepspeech

dmc2gym

OpenAI Gym wrapper for the DeepMind Control Suite

euler

flax

Flax is a neural network library for JAX that is designed for flexibility.

gym-examples

Example code for the Gym documentation

hermione

Code for https://onnoeberhard.com/2019/08/21/cool-logic.html

hockey-rl

Implementations of DQN and TD3, used in the 2021 Reinforcement Learning Hockey tournament of the Autonomous Learning group at the Max-Planck Institute for Intelligent Systems

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

jupyter-launcher

A small jupyter launcher for macos I built

oetils

onnoeberhard

onnoeberhard.github.io

blog

phylo

pontryagin

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

sutton

Solutions to programming exercises in Sutton & Barto (2018)

young

Solutions to data exercises in "University Physics" by Young and Freedman (15e).