nicklashansen Goto Github PK

a3c

Asynchronous Advantage Actor-Critic using Generalized Advantage Estimation (PyTorch)

adaptive-learning-rate-schedule

PyTorch implementation of the "Learning an Adaptive Learning Rate Schedule" paper found here: https://arxiv.org/abs/1909.09712.

awesome-rl-envs

awesome-self-supervised-learning

A curated list of awesome self-supervised methods

bachelor-thesis

Repository for bachelor thesis on Automatic Multi-Modal Detection of Autonomic Arousals in Sleep. The thesis itself and all related data is confidential and thus not publicly available, but access to the thesis can be granted by sending a request to [email protected].

clevr-iep

Inferring and Executing Programs for Visual Reasoning

deep-rl-algos

Collection of deep reinforcement learning algorithm implementations.

dmcontrol-generalization-benchmark

DMControl Generalization Benchmark

docker-from-conda

Builds a docker image from a conda environment.yml file.

me

About me

minimal-nas

Minimal implementation of a Neural Architecture Search system.

music-genre-classification

Exam project on Audio Features for Music Genre Classification for course 02452 Audio Information Processing Systems at Technical University of Denmark (DTU).

nautilus-launcher

Minimal launcher for Nautilus

neural-net-optimization

PyTorch implementations of recent optimization algorithms for deep learning.

nicklashansen.github.io

Repository for my personal site https://nicklashansen.github.io/, built with plain html.

octo

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

pixelcnn-made

PyTorch implementation of the auto-regressive PixelCNN-MADE architecture.

policy-adaptation-during-deployment

Training code and evaluation benchmarks for the "Self-Supervised Policy Adaptation during Deployment" paper.

ppo-procgen-utils

Utility functions for the projects that I supervise in 02456 Deep Learning @ DTU.

puppeteer

Code for "Hierarchical World Models as Visual Whole-Body Humanoid Controllers"

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

reinforcement-learning-dennybritz-exercises

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

reinforcement-learning-sutton-barto

Personal repository for course on reinforcement learning. Includes implementations of various problems from the Reinforcement Learning: An Introduction book by R. Sutton and A. Barto.

rlds_dataset_builder

An example RLDS dataset builder for X-embodiment dataset conversion.

rnn_lstm_from_scratch

How to build RNNs and LSTMs from scratch with NumPy.

smallrl

Personal repository for quick RL prototyping. Work in progress!

svea-vit

Code for the paper "Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation"

tdmpc

Code for "Temporal Difference Learning for Model Predictive Control"

tdmpc2

Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

vae-svhn

Variational Autoencoder (VAE) on the Street View House Numbers (SVHN) dataset.