harvard-edge/QuaRL
QuaRL is an open-source framework for systematically studying the effect of applying quantization to reinforcement learning algorithms.
QuaRL helps machine learning engineers and researchers accelerate the training of reinforcement learning models. It takes your existing reinforcement learning algorithms and environment setups as input. The output is a faster training process, potentially reducing the computational time by 1.5x to 2.5x, without sacrificing model performance or reward metrics. This tool is ideal for those working with computationally intensive deep reinforcement learning applications.
No commits in the last 6 months.
Use this if you need to significantly speed up the training time of your reinforcement learning models while maintaining their performance.
Not ideal if you are looking for new reinforcement learning algorithms or environments rather than optimizing existing ones.
Stars
82
Forks
19
Language
Python
License
—
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/harvard-edge/QuaRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...