phy-q/benchmark
Phy-Q: A Testbed for Physical Reasoning
This project provides a benchmark to test how well AI agents understand and react to real-world physics, similar to how humans or robots do. It takes an AI agent as input and evaluates its ability to solve tasks in a simulated environment based on 15 physical scenarios (like rolling, falling, or structural stability). The output is a "Phy-Q score" that measures the agent's physical reasoning intelligence. This is for AI researchers and developers working on intelligent agents for robotics or other physical interaction systems.
No commits in the last 6 months.
Use this if you are developing or evaluating AI agents that need to reason about physical interactions and make decisions in dynamic environments.
Not ideal if you are looking for a general-purpose AI benchmark that doesn't focus specifically on physical reasoning in simulated environments.
Stars
45
Forks
6
Language
Python
License
MIT
Category
Last pushed
Jul 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/phy-q/benchmark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.