ObjectRL: An Object-Oriented Reinforcement Learning Codebase

TL;DR

ObjectRL is an open-source, object-oriented Python framework that simplifies the development and testing of deep reinforcement learning algorithms, making research more accessible and efficient.

Contribution

It introduces an OOP-based structure for RL codebases, enhancing modularity, clarity, and ease of customization for research purposes.

Findings

Demonstrates flexibility and rapid prototyping capabilities.

Shows improved code organization and reusability.

Facilitates understanding and modification of RL algorithms.

Abstract

ObjectRL is an open-source Python codebase for deep reinforcement learning (RL), designed for research-oriented prototyping with minimal programming effort. Unlike existing codebases, ObjectRL is built on Object-Oriented Programming (OOP) principles, providing a clear structure that simplifies the implementation, modification, and evaluation of new algorithms. ObjectRL lowers the entry barrier for deep RL research by organizing best practices into explicit, clearly separated components, making them easier to understand and adapt. Each algorithmic component is a class with attributes that describe key RL concepts and methods that intuitively reflect their interactions. The class hierarchy closely follows common ontological relationships, enabling data encapsulation, inheritance, and polymorphism, which are core features of OOP. We demonstrate the efficiency of ObjectRL's design through representative use cases that highlight its flexibility and suitability for rapid prototyping. The documentation and source code are available at https://objectrl.readthedocs.io and https://github.com/adinlab/objectrl .