Welcome to ModulaRL Documentation

Note: ModulaRL is currently under construction.

ModulaRL is a highly modular and extensible reinforcement learning library built on PyTorch. It aims to provide researchers and developers with a flexible framework for implementing, experimenting with, and extending various RL algorithms.

Features

• Modular Architecture: Allows easy component swapping and extension.

• Efficient Implementations: Leverages PyTorch’s capabilities for optimal performance.

• Integration with TorchRL: Provides optimized replay buffers and utilities.

• Clear Documentation and Examples: Offers a quick start for users.

• Designed for Research and Practical Applications: Facilitates fast and custom prototyping for researchers with or without RL experience.

Contents:

• Installation Guide
  • Dependencies
  • Verifying the Installation
  • Troubleshooting
• API Reference
  • Agents
  • Policies
  • Replay Buffers
  • Q-Functions
• About

Indices and tables

• Index

• Module Index

• Search Page