Monte Carlo Markov Chain Optimizer

Monte Carlo Markov Chain Optimizer

You define the problem. We do the optimization.

A novel, comprehensive, generic, and extensible Monte Carlo Markov Chain Optimization designing solution.

NOTE：This is the early access version. Therefore, the price may be increased over the versions. As this tool is still developing, all core functions and UI may change with the iterations. The description of the document may deviate from the actual implementation.

Documentation | Discord | Roadmap

Features

• Supports various MCMC & RJ-MCMC optimizations, e.g.,
• simulated annealing (SA)
• pareto simulated annealing (PSA)
• alternating optimization-simulated annealing (AO-SA)
• alternating optimization-pareto simulated annealing (AO-PSA)
• and their reversible-jump Markov chain Monte Carlo (RJ-MCMC) versions.
• It supports seamless switching between all types of optimizers.
• Supports two types of weighting modules. Auto weighting (learning) during the optimization process. Fixed weights specified by the designer.
  
• Visual Formula. Build the cost term formula by using the visual formula without any coding. Thanks to Odin Inspector. We created a smart suggest engine that helps offer the correct type of data for the visual formulas input; it will speed up the performance of forming formulas.
• Visually debugging. It supports taking one move, one simulation, or one evaluation on a single solution step by step to enable the visually debugging ability. No black box in POC anymore!!!
• Completed recording system. It supports us to save the results and load them back for further investigations. It supports all custom data; you don't even need to write any code about saving and loading functions.
• Modularized design.The well-designed and extensible modules are based on the MCMC framework. We provide a set of out-of-the-box core modules, such as the Dominator, Acceptor (Greedy, Probability Acceptor), Movement, Auto Weights modules, etc. These are standardized modules in the MCMC frameworks. Besides, you can also customize those modules according to your problem that needs to be solved.
• Generic design. Using the generic design, you can easily define your problem by extension.
• Monitors. A set of Monitors to inspect the optimizing process in real time.
• Detailed tutorials. It comes with detailed demos that help you to get into the MCMC world.
• Support dual platforms. It works well on Windows and Mac OS. It might work on Linux(not tested).
• Easy to generate results at scale. The optimizer is designed independently without using any Unity Game Object references. Once your optimizer is done, you can make it as a prefab and apply it to the mass results scenes without further modification. The optimizer will automatically hook the items up.
• Full source code.
• More...

Guides

Introduction

Quick Start

Modules

Released Notes

Video

Advanced

Formulas

Custom Formula

Custom Evaluator

Custom Iteration

Custom Movement

Custom Item Parameter

Monitors

Undocumented Handy APIs