# Model-free, Model-based, and General Intelligence

arXiv: https://arxiv.org/abs/1806.02308 · HTML: https://mlsanity.com/paper/1806.02308/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2018.

## Built on by (most cited first, 14 of 14)

- [Argumentative XAI: A Survey](https://mlsanity.com/paper/2105.11266/) (2021)
- [Learning First-Order Representations for Planning from Black-Box States: New Results](https://mlsanity.com/paper/2105.10830/) (2021)
- [Expected Free Energy-based Planning as Variational Inference](https://mlsanity.com/paper/2504.14898/) (2025)
- [Learning Robust Real-Time Cultural Transmission without Human Data](https://mlsanity.com/paper/2203.00715/) (2022)
- [AI Agents as Universal Task Solvers](https://mlsanity.com/paper/2510.12066/) (2025)
- [Time series analysis with dynamic law exploration](https://mlsanity.com/paper/2104.10970/) (2021)
- [Target Languages (vs. Inductive Biases) for Learning to Act and Plan](https://mlsanity.com/paper/2109.07195/) (2021)
- [Graph Learning for Numeric Planning](https://mlsanity.com/paper/2410.24080/) (2024)
- [Active Inference Tree Search in Large POMDPs](https://mlsanity.com/paper/2103.13860/) (2021)
- [Model-free system identification of surface ships in waves via Hankel dynamic mode decomposition with control](https://mlsanity.com/paper/2502.15782/) (2025)
- [On the Configuration of More and Less Expressive Logic Programs](https://mlsanity.com/paper/2203.01024/) (2022)
- ["A Nova Eletricidade: Aplicacc~oes, Riscos e Tendencias da IA Moderna -- "The New Electricity": Applications, Risks, and Trends in Current AI](https://mlsanity.com/paper/2310.18324/) (2023)
- [GRAML: Goal Recognition As Metric Learning](https://mlsanity.com/paper/2505.03941/) (2025)
- [Expected Free Energy-based Planning as Variational Inference](https://mlsanity.com/paper/2606.20658/) (2026)

## Abstract (arXiv)

During the 60s and 70s, AI researchers explored intuitions about intelligence by writing programs that displayed intelligent behavior. Many good ideas came out from this work but programs written by hand were not robust or general. After the 80s, research increasingly shifted to the development of learners capable of inferring behavior and functions from experience and data, and solvers capable of tackling well-defined but intractable models like SAT, classical planning, Bayesian networks, and POMDPs. The learning approach has achieved considerable success but results in black boxes that do not have the flexibility, transparency, and generality of their model-based counterparts. Model-based approaches, on the other hand, require models and scalable algorithms. Model-free learners and model-based solvers have close parallels with Systems 1 and 2 in current theories of the human mind: the first, a fast, opaque, and inflexible intuitive mind; the second, a slow, transparent, and flexible analytical mind. In this paper, I review developments in AI and draw on these theories to discuss the gap between model-free learners and model-based solvers, a gap that needs to be bridged in order to have intelligent systems that are robust and general.