Fetching the paper…
Reading the bibliography…
There exist well-developed frameworks for causal modelling, but these require rather a lot of human domain expertise to define causal variables and perform interventions.
Explanation, invariance, and intervention
Jim Woodward · 1997
Earlier work this paper cites.
Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
Richard S Sutton, Doina Precup, and Satinder Singh · 1999
Earlier work this paper cites.
Temporal abstraction in reinforcement learning
Doina Precup · 2000
Earlier work this paper cites.
Two theorems on invariance and causality
Nancy Cartwright · 2003
Earlier work this paper cites.
Causal inference of ambiguous manipulations
Peter Spirtes and Richard Scheines · 2004
Earlier work this paper cites.
A First Look at Rigorous Probability Theory
Jeffrey Seth Rosenthal · 2006
Earlier work this paper cites.
Causality
Judea Pearl · 2009
Earlier work this paper cites.
Constructor theory
David Deutsch · 2012
Earlier work this paper cites.
Auto-Encoding variational bayes
Diederik P Kingma and Max Welling · 2013
Earlier work this paper cites.
Cyclic causal discovery from continuous equilibrium data
Joris Mooij and Tom Heskes · 2013
Earlier work this paper cites.
Stochastic backpropagation and approximate inference in deep generative models
Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra · 2014
Earlier work this paper cites.
Causal inference using invariant prediction: identification and confidence intervals
Jonas Peters, Peter Bühlmann, and Nicolai Meinshausen · 2015
Earlier work this paper cites.
Multi-Level Cause-Effect systems
Krzysztof Chalupka, Frederick Eberhardt, and Pietro Perona · 2016
Earlier work this paper cites.
Green and grue causal variables
Frederick Eberhardt · 2016
Earlier work this paper cites.
Constructor theory of thermodynamics
Chiara Marletto · 2016
Earlier work this paper cites.
From deterministic ODEs to dynamic structural causal models
Paul K Rubenstein, Stephan Bongers, Bernhard Schoelkopf, and Joris M Mooij · 2016
Earlier work this paper cites.
The problem of variable choice
James Woodward · 2016
Cited alongside, same era.
Independently controllable features
Emmanuel Bengio, Valentin Thomas, Joelle Pineau, Doina Precup, and Yoshua Bengio · 2017
Cited alongside, same era.
Elements of causal inference: foundations and learning algorithms
Jonas Peters, Dominik Janzing, and Bernhard Schölkopf · 2017
Cited alongside, same era.
Causal consistency of structural equation models
Paul K Rubenstein, Sebastian Weichwald, Stephan Bongers, Joris M Mooij, Dominik Janzing, Moritz Grosse-Wentrup, and Bernhard Schölkopf · 2017
Cited alongside, same era.
Independently controllable factors
Valentin Thomas, Jules Pondard, Emmanuel Bengio, Marc Sarfati, Philippe Beaudoin, Marie-Jean Meurs, Joelle Pineau, Doina Precup, and Yoshua Bengio · 2017
Cited alongside, same era.
Causal modeling of dynamical systems
Stephan Bongers, Tineke Blom, and Joris M Mooij · 2018
Cited alongside, same era.
Object-centric learning with slot attention
Locatello, Weissenborn, Unterthiner, Mahendran, Heigold, Uszkoreit, Dosovitskiy, and Kipf · 2020
Later among the works it cites.
Representation learning via invariant causal mechanisms
Jovana Mitrovic, Brian McWilliams, Jacob Walker, Lars Buesing, and Charles Blundell · 2020
Later among the works it cites.
Memory and entropy
Carlo Rovelli · 2020
Later among the works it cites.
Emergent Real-World robotic skills via unsupervised Off-Policy reinforcement learning
Archit Sharma, Michael Ahn, Sergey Levine, Vikash Kumar, Karol Hausman, and Shixiang Gu · 2020
Later among the works it cites.
Causality and independence in perfectly adapted dynamical systems
Tineke Blom and Joris M Mooij · 2021
Later among the works it cites.
Geometric deep learning: Grids, groups, graphs, geodesics, and gauges
Michael M Bronstein, Joan Bruna, Taco Cohen, and Petar Veličković · 2021
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Diversity is all you need: Learning skills without a reward function
B Eysenbach, A Gupta, J Ibarz, and S Levine · 2018
Cited alongside, same era.
Challenging common assumptions in the unsupervised learning of disentangled representations
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, and Olivier Bachem · 2018
Cited alongside, same era.
The book of why: the new science of cause and effect
Judea Pearl and Dana Mackenzie · 2018
Cited alongside, same era.
Invariant risk minimization
Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, and David Lopez-Paz · 2019
Cited alongside, same era.
Abstracting causal models
Sander Beckers and Joseph Y Halpern · 2019
Cited alongside, same era.
Approximate causal abstraction
Sander Beckers, Frederick Eberhardt, and Joseph Y Halpern · 2019
Cited alongside, same era.
Later among the works it cites.
Variable definition and independent components
Lorenzo Casini, Alessio Moneta, and Marco Capasso · 2021
Later among the works it cites.
Equivariant Convolutional Networks
Taco Cohen · 2021
Later among the works it cites.
Causal abstractions of neural networks
Geiger, Lu, Icard, and Potts · 2021
Later among the works it cites.
Towards causal representation learning
Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, and Yoshua Bengio · 2021
Later among the works it cites.
Desiderata for representation learning: A causal perspective
Yixin Wang and Michael I Jordan · 2021
Later among the works it cites.
A Theory of Abstraction in Reinforcement Learning
David Abel · 2022
Closest in time.
On pearl’s hierarchy and the foundations of causal inference, 2022
Elias Bareinboim, Juan D Correa, Duligur Ibeling, and Thomas Icard · 2022
Closest in time.
Weakly supervised causal representation learning
Johann Brehmer, Pim de Haan, Phillip Lippe, and Taco Cohen · 2022
Closest in time.
CITRIS: Causal identifiability from temporal intervened sequences
Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M Asano, Taco Cohen, and Efstratios Gavves · 2022
Closest in time.
Learning by doing: Controlling a dynamical system using causality, control, and reinforcement learning
Sebastian Weichwald, Søren Wengel Mogensen, Tabitha Edith Lee, Dominik Baumann, Oliver Kroemer, Isabelle Guyon, Sebastian Trimpe, Jonas Peters, and Niklas Pfister · 2022
Closest in time.