https://github.com/devspaceship/madepro

A minimal Rust library for solving finite deterministic Markov decision processes
https://github.com/devspaceship/madepro

markov-decision-processes mdp q-learning reinforcement-learning rust sarsa temporal-difference

Last synced: 13 days ago
JSON representation

A minimal Rust library for solving finite deterministic Markov decision processes

• Host: GitHub
• URL: https://github.com/devspaceship/madepro
• Owner: devspaceship
• License: mit
• Created: 2023-12-23T13:19:56.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-09-10T00:51:03.000Z (over 1 year ago)
• Last Synced: 2025-09-19T13:13:02.851Z (8 months ago)
• Topics: markov-decision-processes, mdp, q-learning, reinforcement-learning, rust, sarsa, temporal-difference
• Language: Rust
• Homepage: https://crates.io/crates/madepro
• Size: 64.5 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# madepro

A minimal Rust library crate for solving finite deterministic

Markov decision processes (MDPs).

The name of the library comes from the first syllable of each word.

## Limitations

This library is still in development and is not ready for production use.

It only implements a few algorithms and one environment.

It is also limited to deterministic MDPs.

Originally, I only created this library in order to refactor my blog post

on [Markov Decision Processes](https://devspaceship.com/posts/gridworld).

However, I decided to probably continue working on it when I have the time.

In the future I would first like to make the library more generic

and then add more algorithms and environments.

## Features

The library currently supports the following algorithms:

- [Policy Iteration](https://en.wikipedia.org/wiki/Markov_decision_process#Policy_iteration)

- [Value Iteration](https://en.wikipedia.org/wiki/Markov_decision_process#Value_iteration)

- [SARSA](https://en.wikipedia.org/wiki/State-Action-Reward-State-Action)

- [Q-Learning](https://en.wikipedia.org/wiki/Q-learning)

## Roadmap

The following features are planned for the future:

- Stochastic MDPs

- Stochastic policies

- State-dependent action spaces

- More algorithms