WassimTenachi/PhySO
PhySO uses deep reinforcement learning for symbolic regression to discover analytical physical laws from experimental data.
Not currently ranked — collecting fresh signals.
star history
Physical Symbolic Optimization (PhySO) is a Python package that performs symbolic regression using deep reinforcement learning to discover mathematical equations that fit scientific data. The system searches the space of functional forms and dimensional constraints to find analytically correct physical laws. It supports multi-dataset regression, uncertainty-aware fitting, and incorporates dimensional analysis for physics-based constraints.
Frequently asked
- What is WassimTenachi/PhySO?
- PhySO uses deep reinforcement learning for symbolic regression to discover analytical physical laws from experimental data.
- Is PhySO open source?
- Yes — WassimTenachi/PhySO is open source, released under the MIT license.
- What language is PhySO written in?
- WassimTenachi/PhySO is primarily written in Python.
- How popular is PhySO?
- WassimTenachi/PhySO has 2k stars on GitHub.
- Where can I find PhySO?
- WassimTenachi/PhySO is on GitHub at https://github.com/WassimTenachi/PhySO.