Stars
Repository for the paper "Combining Deep and Imitation Learning for Stable Visual Servoing using the Large Projection Formulation"
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
PyTorch code and models for the DINOv2 self-supervised learning method.
Layerwise Batch Entropy Regularization
Tips and tricks to optimize your C++ code
Graphical Editor to create BehaviorTrees. Compliant with BehaviorTree.CPP
Behavior Trees Library in C++. Batteries included.
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
SmartStart exploration method for reinforcement learning algorithms.
ODE2VAE: Deep generative second order ODEs with Bayesian neural networks
code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
Materials of the Nordic Probabilistic AI School 2021.
Official implementation of the paper "Increasing the adversarial robustness and explainability of capsule networks with γ-capsules"
An open source explorer for your remarkable tablet to show, upload or delete files via the remarkable cloud.
Official implementation of the paper "Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks".
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
S-RL Toolbox: Reinforcement Learning (RL) and State Representation Learning (SRL) for Robotics
TikZ library for drawing Bayesian networks, graphical models and (directed) factor graphs in LaTeX.
A collection of tools and plugins for Gazebo
Provides a simple simulation interface and template for setting up a hardware interface for ros_control
An Open Source Machine Learning Framework for Everyone
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
A toolkit for developing and comparing reinforcement learning algorithms.
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.