# Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning

arXiv: https://arxiv.org/abs/1911.11185 · HTML: https://mlsanity.com/paper/1911.11185/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2019.

## Built on by (most cited first, 11 of 11)

- [Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution](https://mlsanity.com/paper/2103.14230/) (2021)
- [ACRE: Abstract Causal REasoning Beyond Covariation](https://mlsanity.com/paper/2103.14232/) (2021)
- [MEWL: Few-shot multimodal word learning with referential uncertainty](https://mlsanity.com/paper/2306.00503/) (2023)
- [Active Reasoning in an Open-World Environment](https://mlsanity.com/paper/2311.02018/) (2023)
- [A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics](https://mlsanity.com/paper/2103.01403/) (2021)
- [Causality from Bottom to Top: A Survey](https://mlsanity.com/paper/2403.11219/) (2024)
- [Gap Minimization for Knowledge Sharing and Transfer](https://mlsanity.com/paper/2201.11231/) (2022)
- [A General Framework for the Representation of Function and Affordance: A Cognitive, Causal, and Grounded Approach, and a Step Toward AGI](https://mlsanity.com/paper/2206.05273/) (2022)
- [Using Human-Guided Causal Knowledge for More Generalized Robot Task Planning](https://mlsanity.com/paper/2110.04664/) (2021)
- [Blood Glucose Control Via Pre-trained Counterfactual Invertible Neural Networks](https://mlsanity.com/paper/2405.17458/) (2024)
- [Grounding Before Generalizing: How AI Differs from Humans in Causal Transfer](https://mlsanity.com/paper/2604.24062/) (2026)

## Abstract (arXiv)

Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed with two basic yet general theories for transfer learning: (i) a task shares a common abstract structure that is invariant across domains, and (ii) the behavior of specific features of the environment remain constant across domains. We adopt a Bayesian perspective of causal theory induction and use these theories to transfer knowledge between environments. Given these general theories, the goal is to train an agent by interactively exploring the problem space to (i) discover, form, and transfer useful abstract and structural knowledge, and (ii) induce useful knowledge from the instance-level attributes observed in the environment. A hierarchy of Bayesian structures is used to model abstract-level structural causal knowledge, and an instance-level associative learning scheme learns which specific objects can be used to induce state changes through interaction. This model-learning scheme is then integrated with a model-based planner to achieve a task in the OpenLock environment, a virtual ``escape room'' with a complex hierarchy that requires agents to reason about an abstract, generalized causal structure. We compare performances against a set of predominate model-free reinforcement learning(RL) algorithms. RL agents showed poor ability transferring learned knowledge across different trials. Whereas the proposed model revealed similar performance trends as human learners, and more importantly, demonstrated transfer behavior across trials and learning situations.