Robert Tjarko Lange

gymnax. RL Environments in JAX 🌍

evosax. Evolution Strategies in JAX 🦎

code-and-blog. Some small scale experiments for my blog posts 📝

gymnax-blines. Baselines for gymnax 🤖

reading-notes-ml. Progress, Notes, Summaries and a lot of Questions on Machine Learning

spinningup-workspace. Reading notes & PyTorch experiments on OpenAI's "Spinning Up in DRL" tutorial.

agentlens. Local in-depth observability for coding-agent sessions 🔎

deep-rl-tutorial. A Tutorial on Deep Reinforcement Learning in PyTorch

flexible-learning-group. A curated list of papers presented in the 📖"Flexible Learning Reading Group" @ TU Berlin. Join us! 🤗

headless-cli. One unified CLI for headless coding agent execution 🤖

es-lottery. Lottery Tickets in Evolutionary Optimization (Lange & Sprekeler, ICML 2023)

gym-hanoi. A Towers of Hanoi environment in OpenAI Gym Style

minimal-meta-rl. Minimal A2C/A3C example of an LSTM-based meta-learner.

SequentialBayesianLearning. Sequential Bayesian Learning Agents learning data-generating process of binary sequence.

automata-perturbation-lstm. Code accompanying Gómez-Nava et al. (2023, Nature Physics)

gym-swarm. A Swarm environment in OpenAI gym style

StochVol_HMM. Stochastic Volatility Modelling using Hidden Markov Model

algonauts-2021. Algonauts 2021 Challenge Mini-Track submission based on SimCLR-v2 features & Bayesian Optimization

action-grammars-hrl. Action Grammars for Hierarchical Reinforcement Learning

evojax-benchmarks. Benchmarking Utilities for EvoJAX

Reading_Notes_Neuro. Progress, Notes, Summaries and a lot of Questions on Neuroscience

PlotNeuralNet. Latex code for making neural networks diagrams

Bio-Plausible-DeepLearning. Who needs backprop? - Guerguiev et al (2017) - Reproduction & Robustness Checks

RobertTLange.

hibiki. An agent-first text-to-speech MacOS app & CLI 🎙️

todui. An Agent-Human Todo TUI App 📋

ModelsNeuralSystems. Computer Practical Coursework for BCCN Berlin course "Models of Neural Systems" (2018/2019)

python-markdown-generator. Python library for dynamically generating HTML sanitised Markdown syntax.

evojax. Jupyter Notebook

markdown. A Python implementation of John Gruber’s Markdown with Extension support.

picknmix. A simple tool to help building stacking models.

sequitur. Automatically exported from code.google.com/p/sequitur

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

rlpyt. Reinforcement Learning in PyTorch

Lexis. Lexis: An Optimization Framework for Discovering the Hierarchical Structure of Sequential Data

pybullet-gym. Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.

mistral-jax. JAX implementation of the Mistral model

Migration_and_Technology_Diffusion. Bachelor Thesis tackling the Impact of Skilled-Worker Immigration on the Diffusion of New Technologies

RandGLM. RandNLA methods for estimating GLMs with Big Datasets