Related papers: Robust agents learn causal world models

Robust agents learn causal world models

URL: http://arxiv.org/abs/2402.10877v7
Date: Fri, 19 Jul 2024 11:12:08 GMT
Title: Robust agents learn causal world models
Authors: Jonathan Richens, Tom Everitt,
Abstract summary: We show that any agent capable of satisfying a regret bound under a large set of distributional shifts must have learned an approximate causal model of the data generating process. We discuss the implications of this result for several research areas including transfer learning and causal inference.
Score: 7.845222238426246
License: http://creativecommons.org/licenses/by/4.0/
Abstract: It has long been hypothesised that causal reasoning plays a fundamental role in robust and general intelligence. However, it is not known if agents must learn causal models in order to generalise to new domains, or if other inductive biases are sufficient. We answer this question, showing that any agent capable of satisfying a regret bound under a large set of distributional shifts must have learned an approximate causal model of the data generating process, which converges to the true causal model for optimal agents. We discuss the implications of this result for several research areas including transfer learning and causal inference.

Related papers

Identifiable Latent Neural Causal Models [82.14087963690561]
Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
arXiv Detail & Related papers (2024-03-23T04:13:55Z)
The Essential Role of Causality in Foundation World Models for Embodied AI [102.75402420915965]
Embodied AI agents will require the ability to perform new tasks in many different real-world environments. Current foundation models fail to accurately model physical interactions and are therefore insufficient for Embodied AI. The study of causality lends itself to the construction of veridical world models.
arXiv Detail & Related papers (2024-02-06T17:15:33Z)
Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations [62.48505112245388]
We take an in-depth look at the causal awareness of modern representations of agent interactions. We show that recent representations are already partially resilient to perturbations of non-causal agents. We propose a metric learning approach that regularizes latent representations with causal annotations.
arXiv Detail & Related papers (2023-12-07T18:57:03Z)
Identifiable Latent Polynomial Causal Models Through the Lens of Change [82.14087963690561]
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability.
arXiv Detail & Related papers (2023-10-24T07:46:10Z)
Discovering Agents [10.751378433775606]
Causal models of agents have been used to analyse the safety aspects of machine learning systems. This paper proposes the first formal causal definition of agents -- roughly that agents are systems that would adapt their policy if their actions influenced the world in a different way.
arXiv Detail & Related papers (2022-08-17T15:13:25Z)
Active Bayesian Causal Inference [72.70593653185078]
We propose Active Bayesian Causal Inference (ABCI), a fully-Bayesian active learning framework for integrated causal discovery and reasoning. ABCI jointly infers a posterior over causal models and queries of interest. We show that our approach is more data-efficient than several baselines that only focus on learning the full causal graph.
arXiv Detail & Related papers (2022-06-04T22:38:57Z)
Causality Inspired Representation Learning for Domain Generalization [47.574964496891404]
We introduce a general structural causal model to formalize the Domain generalization problem. Our goal is to extract the causal factors from inputs and then reconstruct the invariant causal mechanisms. We highlight that ideal causal factors should meet three basic properties: separated from the non-causal ones, jointly independent, and causally sufficient for the classification.
arXiv Detail & Related papers (2022-03-27T08:08:33Z)
Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization [17.825841580342715]
Machine learning robustness and domain generalization are fundamentally correlated. Recent studies show that more robust (adversarially trained) models are more generalizable. There is a lack of theoretical understanding of their fundamental connections.
arXiv Detail & Related papers (2022-02-03T20:26:27Z)
A General Framework for Distributed Inference with Uncertain Models [14.8884251609335]
We study the problem of distributed classification with a network of heterogeneous agents. We build upon the concept of uncertain models to incorporate the agents' uncertainty in the likelihoods.
arXiv Detail & Related papers (2020-11-20T22:17:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.