PufferAI/PufferLib

Puffing up reinforcement learning

What it solves

PufferLib is designed to make reinforcement learning (RL) faster and more accessible by providing a library that can train small, high-performance models that achieve super-human performance in seconds.

How it works

The library implements a custom learning algorithm, hyperparameter tuning, and simulation methods based on the team's own research to optimize the training process.

Who it’s for

It is intended for developers and researchers who need a high-performance reinforcement learning framework for their applications.

Highlights

  • Fast training speeds capable of producing super-human models in seconds.
  • Includes built-in hyperparameter tuning and simulation methods.
  • Free and open source.

Related

  • Project
    leggedrobotics/rsl_rl

    A GPU-accelerated, lightweight learning library for robotics research that enables rapid prototyping of robot learning algorithms.

  • Project
    huggingface/peft

    A library providing state-of-the-art parameter-efficient fine-tuning methods to adapt large pretrained models using minimal compute and storage.

  • Project
    Denys88/rl_games

    A high-performance reinforcement learning library implemented in PyTorch that optimizes training speed through Triton kernels and GPU-accelerated simulation pipelines.

  • Project
    ServiceNow/Fast-LLM

    A high-performance library for training large language models that uses 3D parallelism and optimized kernels to reduce training time and cost.

  • Dispatch
    🤗 PEFT library release enables parameter-efficient fine-tuning of billion‑scale models

    Hugging Face announced the 🤗 PEFT library, which lets users fine‑tune billion‑parameter models on low‑resource hardware by training only a tiny fraction of parameters.