MINERVA

An out-of-the-box GUI tool for offline deep reinforcement learning

GitHub Documentation

The world's first deep reinforcement learning software for everyone.

MINERVA provides extremely powerful deep reinforcement learning algoriths through the stunning GUI. You can start reinforcement learning projects with the minimum lines of codes.

features

ALL YOU NEED IS A DATASET

MINERVA only requires datasets to start offline deep reinforcement learning. Any combinations of vector observations and image observations with discrete actions and continuous actions are supported.

STUNNING GUI

MINERVA provides designed with intuitive GUI to let everyone lerverage extremely powerful algorithms without barriers. The GUI is developed as a Single Page Application (SPA) to make it work in the eye-opening speed.

POWERFUL ALGORITHMS

MINERVA is powered by d3rlpy, a powerful offline deep reinforcement learning library for Python, to provide extremely powerful algorithms in an out-of-the-box way. The trained policy can be exported as TorchScript and ONNX.

the new deep reinforcement learning experience

Dataset Management

Datasets can be easily uploaded to manage and visualize statistical information.

Out-Of-The-Box Policy Training

Start training deep reinforcement learning algorithms without coding while visualizing metrics.

Exporting Inference Model

The trained policy can be exported as TorchScript and ONNX format for deployment.

video

core library

d3rlpy

An offline deep reinforcement learning library

d3rlpy is a Python library providing the state-of-the-art offline deep reinforcement learning algorithms through scikit-learn style API.

Project Page