PHYRE: A New Benchmark for Physical Reasoning

08/15/2019
by   Anton Bakhtin, et al.
6

Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The benchmark is designed to encourage the development of learning algorithms that are sample-efficient and generalize well across puzzles. We test several modern learning algorithms on PHYRE and find that these algorithms fall short in solving the puzzles efficiently. We expect that PHYRE will encourage the development of novel sample-efficient agents that learn efficient but useful models of physics. For code and to play PHYRE for yourself, please visit https://player.phyre.ai.

READ FULL TEXT

page 15

page 16

page 17

research
10/13/2021

OPEn: An Open-ended Physics Environment for Learning Without a Task

Humans have mental models that allow them to plan, experiment, and reaso...
research
06/17/2021

Hi-Phy: A Benchmark for Hierarchical Physical Reasoning

Reasoning about the behaviour of physical objects is a key capability of...
research
08/31/2021

Phy-Q: A Benchmark for Physical Reasoning

Humans are well-versed in reasoning about the behaviors of physical obje...
research
08/05/2023

Physics-Based Task Generation Through Causal Sequence of Physical Interactions

Performing tasks in a physical environment is a crucial yet challenging ...
research
04/07/2021

PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Simulated virtual environments serve as one of the main driving forces b...
research
11/14/2020

Solving Physics Puzzles by Reasoning about Paths

We propose a new deep learning model for goal-driven tasks that require ...
research
03/25/2021

The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI

We introduce a visually-guided and physics-driven task-and-motion planni...

Please sign up or login with your details

Forgot password? Click here to reset