NLNS
or-gym
| NLNS | or-gym | |
|---|---|---|
| 1 | 2 | |
| 71 | 359 | |
| - | - | |
| 1.8 | 0.0 | |
| almost 4 years ago | 7 months ago | |
| Python | Python | |
| GNU General Public License v3.0 only | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
NLNS
-
[D] What type of machine learning can be used to solve timetable optimisation problems?
I do not believe anyone has tried ML methods for solving timetable problems yet, so this would be new. My group has come up with several different options for ML+Optimization, but probably our approach "Neural Large Neighborhood Search" will be the most promising here. See our ECAI paper: https://ecai2020.eu/papers/786_paper.pdf, medium post explaining the method: https://dot-bielefeld.medium.com/learning-improvement-heuristics-for-vehicle-routing-problems-with-neural-large-neighborhood-search-6e19252e85f4 and source code: https://github.com/ahottung/NLNS.
or-gym
-
Gym like frameworks for combinatorial optimization on Graphs?
How about ORGym: https://github.com/hubbs5/or-gym ?
-
Is there a reinforcement learning method to find stock policy for single echelon inventory system ?
Specifically, inputs to I0 through L should be 1-column arrays: https://github.com/hubbs5/or-gym/blob/d5fbc73623c7b197316d33fba094105953889df3/or_gym/envs/supply_chain/inventory_management.py#L46
What are some alternatives?
polyaxon - MLOps Tools For Managing & Orchestrating The Machine Learning LifeCycle
pytorch-a2c-ppo-acktr-gail - PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
VeRyPy - A python library with implementations of 15 classical heuristics for the capacitated vehicle routing problem.
ml4vrp - Geometric Deep Learning Models for Vehicle Routing Problem
maro - Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
tensor2tensor - Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
DeepBeerInventory-RL - The code for the SRDQN algorithm to train an agent for the beer game problem
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
OpenGraphGym
d2l-en - Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.