Physical Reasoning Using Dynamics-Aware Models

by   Eltayeb Ahmed, et al.

A common approach to solving physical-reasoning tasks is to train a value learner on example tasks. A limitation of such an approach is it requires learning about object dynamics solely from reward values assigned to the final state of a rollout of the environment. This study aims to address this limitation by augmenting the reward value with additional supervisory signals about object dynamics. Specifically,we define a distance measure between the trajectory of two target objects, and use this distance measure to characterize the similarity of two environment rollouts.We train the model to correctly rank rollouts according to this measure in addition to predicting the correct reward. Empirically, we find that this approach leads to substantial performance improvements on the PHYRE benchmark for physical reasoning: our approach obtains a new state-of-the-art on that benchmark.



There are no comments yet.


page 1

page 2

page 3

page 4


Forward Prediction for Physical Reasoning

Physical reasoning requires forward prediction: the ability to forecast ...

COPHY: Counterfactual Learning of Physical Dynamics

Understanding causes and effects in mechanical systems is an essential c...

Hi-Phy: A Benchmark for Hierarchical Physical Reasoning

Reasoning about the behaviour of physical objects is a key capability of...

Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction

Value functions are crucial for model-free Reinforcement Learning (RL) t...

Learning Generalizable Physical Dynamics of 3D Rigid Objects

Humans have a remarkable ability to predict the effect of physical inter...

Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images

In this paper, we study the challenging problem of predicting the dynami...

Solving Physics Puzzles by Reasoning about Paths

We propose a new deep learning model for goal-driven tasks that require ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.