Language-Based Causal Representation Learning

07/12/2022
by   Blai Bonet, et al.
0

Consider the finite state graph that results from a simple, discrete, dynamical system in which an agent moves in a rectangular grid picking up and dropping packages. Can the state variables of the problem, namely, the agent location and the package locations, be recovered from the structure of the state graph alone without having access to information about the objects, the structure of the states, or any background knowledge? We show that this is possible provided that the dynamics is learned over a suitable domain-independent first-order causal language that makes room for objects and relations that are not assumed to be known. The preference for the most compact representation in the language that is compatible with the data provides a strong and meaningful learning bias that makes this possible. The language of structured causal models (SCMs) is the standard language for representing (static) causal models but in dynamic worlds populated by objects, first-order causal languages such as those used in "classical AI planning" are required. While "classical AI" requires handcrafted representations, similar representations can be learned from unstructured data over the same languages. Indeed, it is the languages and the preference for compact representations in those languages that provide structure to the world, uncovering objects, relations, and causes.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/05/2013

Compact Representations of Extended Causal Models

Judea Pearl was the first to propose a definition of actual causation us...
research
07/18/2020

Structure Mapping for Transferability of Causal Models

Human beings learn causal models and constantly use them to transfer kno...
research
03/31/2022

Continuous Scene Representations for Embodied AI

We propose Continuous Scene Representations (CSR), a scene representatio...
research
02/02/2023

Unpaired Multi-Domain Causal Representation Learning

The goal of causal representation learning is to find a representation o...
research
04/02/2022

Do learned representations respect causal relationships?

Data often has many semantic attributes that are causally associated wit...
research
05/08/2014

FO(C): A Knowledge Representation Language of Causality

Cause-effect relations are an important part of human knowledge. In real...
research
09/15/2021

Target Languages (vs. Inductive Biases) for Learning to Act and Plan

Recent breakthroughs in AI have shown the remarkable power of deep learn...

Please sign up or login with your details

Forgot password? Click here to reset