%0 Generic %1 genewein2020algorithms %A Genewein, Tim %A McGrath, Tom %A Déletang, Grégoire %A Mikulik, Vladimir %A Martic, Miljan %A Legg, Shane %A Ortega, Pedro A. %D 2020 %K Data %T Algorithms for Causal Reasoning in Probability Trees %U http://arxiv.org/abs/2010.12237 %X Probability trees are one of the simplest models of causal generative processes. They possess clean semantics and -- unlike causal Bayesian networks -- they can represent context-specific causal dependencies, which are necessary for e.g. causal induction. Yet, they have received little attention from the AI and ML community. Here we present concrete algorithms for causal reasoning in discrete probability trees that cover the entire causal hierarchy (association, intervention, and counterfactuals), and operate on arbitrary propositional and causal events. Our work expands the domain of causal reasoning to a very general class of discrete stochastic processes.

@misc{genewein2020algorithms, abstract = {Probability trees are one of the simplest models of causal generative processes. They possess clean semantics and -- unlike causal Bayesian networks -- they can represent context-specific causal dependencies, which are necessary for e.g. causal induction. Yet, they have received little attention from the AI and ML community. Here we present concrete algorithms for causal reasoning in discrete probability trees that cover the entire causal hierarchy (association, intervention, and counterfactuals), and operate on arbitrary propositional and causal events. Our work expands the domain of causal reasoning to a very general class of discrete stochastic processes.}, added-at = {2020-11-09T23:55:42.000+0100}, author = {Genewein, Tim and McGrath, Tom and Déletang, Grégoire and Mikulik, Vladimir and Martic, Miljan and Legg, Shane and Ortega, Pedro A.}, biburl = {https://www.bibsonomy.org/bibtex/22df12b7b3dbc59afa87e8d2d5c6ca9f0/rob8718}, description = {Algorithms for Causal Reasoning in Probability Trees}, interhash = {08f39369550b4a6087c5eae579b567f6}, intrahash = {2df12b7b3dbc59afa87e8d2d5c6ca9f0}, keywords = {Data}, note = {cite arxiv:2010.12237Comment: 11 pages, 8 figures, 5 algorithms. A companion Colaboratory tutorial is available at https://github.com/deepmind/deepmind-research/causal-reasoning}, timestamp = {2020-11-09T23:55:42.000+0100}, title = {Algorithms for Causal Reasoning in Probability Trees}, url = {http://arxiv.org/abs/2010.12237}, year = 2020 }