bnb32 / RL-equation-solver

Reinforcement learning based equation solver using various neural networks implemented in PyTorch

Home Page:https://bnb32.github.io/RL-equation-solver/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Welcome to RL-Equation-Solver!

Documentation CI Code style: black codecov MIT License

This software is an equation solver using various neural networks implemented in PyTorch.

Installing RL-equation-solver

NOTE: The installation instruction below assume that you have python installed on your machine and are using conda as your package/environment manager.

Option 1: Clone repo (recommended for developers)

  1. from home dir, git clone git@github.com:bnb32/RL-equation-solver.git

  2. Create rl_solver environment and install package
    1. Create a conda env: conda create -n rl_solver
    2. Run the command: conda activate rl_solver
    3. cd into the repo cloned in 1.
    4. Prior to running pip below, make sure the branch is correct (install from main!)
    5. Install rl_solver and its dependencies by running: pip install . (or pip install -e . if running a dev branch or working on the source code)
  3. To use pytorch with cuda make sure you have cuda installed and then run the following command:

    pip install torch==2.0.0+cu117 torchvision==0.15.1+cu117 torchaudio==2.0.0+cu117 -f https://download.pytorch.org/whl/torch_stable.html

About

Reinforcement learning based equation solver using various neural networks implemented in PyTorch

https://bnb32.github.io/RL-equation-solver/

License:MIT License


Languages

Language:Jupyter Notebook 97.1%Language:Python 2.9%Language:Makefile 0.1%