# Causality in the human niche: lessons for machine learning

arXiv: https://arxiv.org/abs/2506.13803 · HTML: https://mlsanity.com/paper/2506.13803/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 125 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Builds on (most cited first, 30 of 31)

- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [First return, then explore](https://mlsanity.com/paper/2004.12919/) (2020)
- [Causal Discovery with Continuous Additive Noise Models](https://mlsanity.com/paper/1309.6779/) (2013)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [On Calibration and Out-of-domain Generalization](https://mlsanity.com/paper/2102.10395/) (2021)
- [Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding](https://mlsanity.com/paper/2007.10930/) (2020)
- [Causal Consistency of Structural Equation Models](https://mlsanity.com/paper/1707.00819/) (2017)
- [Learning Neural Causal Models from Unknown Interventions](https://mlsanity.com/paper/1910.01075/) (2019)
- [The Blessings of Multiple Causes](https://mlsanity.com/paper/1805.06826/) (2018)
- [The Causal-Neural Connection: Expressiveness, Learnability, and Inference](https://mlsanity.com/paper/2107.00793/) (2021)
- [Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search](https://mlsanity.com/paper/1811.06272/) (2018)
- [Weakly Supervised Disentanglement with Guarantees](https://mlsanity.com/paper/1910.09772/) (2019)
- [Discovering Causal Signals in Images](https://mlsanity.com/paper/1605.08179/) (2016)
- [Hindsight Credit Assignment](https://mlsanity.com/paper/1912.02503/) (2019)
- [On the Expressivity of Markov Reward](https://mlsanity.com/paper/2111.00876/) (2021)
- [Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration](https://mlsanity.com/paper/2002.09253/) (2020)
- [Approximate Causal Abstraction](https://mlsanity.com/paper/1906.11583/) (2019)
- [Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics](https://mlsanity.com/paper/1706.04317/) (2017)
- [Learning Sparse Causal Models is not NP-hard](https://mlsanity.com/paper/1309.6824/) (2013)
- [Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning](https://mlsanity.com/paper/2107.12544/) (2021)
- [Learning Neural Causal Models with Active Interventions](https://mlsanity.com/paper/2109.02429/) (2021)
- [Time-Agnostic Prediction: Predicting Predictable Video Frames](https://mlsanity.com/paper/1808.07784/) (2018)
- [Causal Induction from Visual Observations for Goal Directed Tasks](https://mlsanity.com/paper/1910.01751/) (2019)
- [Zero-shot causal learning](https://mlsanity.com/paper/2301.12292/) (2023)
- [Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning](https://mlsanity.com/paper/1609.04212/) (2016)
- [Towards a Grounded Theory of Causation for Embodied AI](https://mlsanity.com/paper/2206.13973/) (2022)
- [On Open-Universe Causal Reasoning](https://mlsanity.com/paper/1907.02170/) (2019)
- [Prospective Learning: Principled Extrapolation to the Future](https://mlsanity.com/paper/2201.07372/) (2022)

## Built on by (most cited first, 1 of 1)

- [Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem](https://mlsanity.com/paper/2507.13920/) (2025)

## Abstract (arXiv)

Humans interpret the world around them in terms of cause and effect and communicate their understanding of the world to each other in causal terms. These causal aspects of human cognition are thought to underlie humans' ability to generalize and learn efficiently in new domains, an area where current machine learning systems are weak. Building human-like causal competency into machine learning systems may facilitate the construction of effective and interpretable AI. Indeed, the machine learning community has been importing ideas on causality formalized by the Structural Causal Model (SCM) framework, which provides a rigorous formal language for many aspects of causality and has led to significant advances. However, the SCM framework fails to capture some salient aspects of human causal cognition and has likewise not yet led to advances in machine learning in certain critical areas where humans excel. We contend that the problem of causality in the ``human niche'' -- for a social, autonomous, and goal-driven agent sensing and acting in the world in which humans live -- is quite different from the kind of causality captured by SCMs. For example, everyday objects come in similar types that have similar causal properties, and so humans readily generalize knowledge of one type of object (cups) to another related type (bowls) by drawing causal analogies between objects with similar properties, but such analogies are at best awkward to express in SCMs. We explore how such causal capabilities are adaptive in, and motivated by, the human niche. By better appreciating properties of human causal cognition and, crucially, how those properties are adaptive in the niche in which humans live, we hope that future work at the intersection of machine learning and causality will leverage more human-like inductive biases to create more capable, controllable, and interpretable systems.