Wouter Kool

attention-learn-to-route. Attention based model for learning to solve different routing problems

dpdp. DPDP

stochastic-beam-search. Implementation of Stochastic Beam Search using Fairseq

estimating-gradients-without-replacement. Estimating Gradients for Discrete Random Variables by Sampling without Replacement

ancestral-gumbel-top-k-sampling. Ancestral Gumbel-Top-k Sampling

rl4co. A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

react-native-looped-carousel. :carousel_horse: Looped carousel for React Native

ilikeclr. IlikeCLR

HGS-CVRP. Modern implementation of the hybrid genetic search (HGS) algorithm specialized to the capacitated vehicle routing problem (CVRP). This code also includes an additional neighborhood called SWAP*.

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

VRPLIB. Python library for reading and downloading benchmark instances from the Capacitated Vehicle Routing Library (CVRPLIB).

set-finder-app-landing-page. Get an awesome landing page for your iOS app in less than 30 seconds

jupyter-gym-vnc. A Docker image to run the OpenAI Gym environment in Jupyter notebooks. No host system X11 support needed, graphical parts of the Gym are visible by VNC.

pyconcorde. Python wrapper around the Concorde TSP solver

pytorch-a2c-ppo-acktr. PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).

MNISET. MNIST like dataset with SET card images