Skip to content

DarkZant/rl-continuous

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

rl-continuous

A clean, modular implementation of continuous-action reinforcement learning (RL) algorithms and environments, designed for experimentation, benchmarking, and applied research.

This repository was developed in the context of the IFT6162 – Reinforcement Learning course at Mila and the Université de Montréal, and closely follows the methodology and notation of Pierre-Luc Bacon’s RL book.


Features

  • Continuous-control RL algorithms implemented from scratch
  • Custom Gymnasium-compatible environments for training and evaluation
  • Realistic industrial environments inspired by a flash clay calciner used in cement production
  • Clear code structure, suitable for learning, research, and extension

Repository Structure

algorithms/

Implementation of continuous-action reinforcement learning algorithms:

  • REINFORCE – Monte Carlo policy gradient method
  • PPO (Proximal Policy Optimization) – On-policy actor–critic with clipped objective
  • TD3 (Twin Delayed DDPG) – Off-policy algorithm for continuous control

All implementations are aligned with the formulations presented in the reference book.


gym-continuous/

A collection of custom continuous Gymnasium environments used to train and evaluate the algorithms.

  • Fully compatible with Gymnasium APIs
  • Designed for reproducibility and controlled experimentation

calciner/ (Flash Clay Calciner Environments)

A set of environments modeling a real-world flash clay calciner, an industrial system used in cement manufacturing.

  • Focused on realistic dynamics and control constraints
  • Heavily inspired by the calciner environments from the IFT6162 homework repository
  • Suitable for testing RL methods in applied, high-dimensional control settings

Credits

Developed in collaboration with:

As part of the IFT6162 - Reinforcement Learning course at Mila and the Université de Montréal.

About

Reinforcement learning algorithms with continuous actions for gymnasium-like environments

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages