# Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics

arXiv: https://arxiv.org/abs/1706.04317 · HTML: https://mlsanity.com/paper/1706.04317/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2017.

## Built on by (most cited first, 30 of 58)

- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment](https://mlsanity.com/paper/2402.12275/) (2024)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning](https://mlsanity.com/paper/2302.04419/) (2023)
- [What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models](https://mlsanity.com/paper/2507.06952/) (2025)
- [A Survey on Causal Reinforcement Learning](https://mlsanity.com/paper/2302.05209/) (2023)
- [Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution](https://mlsanity.com/paper/2103.14230/) (2021)
- [Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning](https://mlsanity.com/paper/2105.14074/) (2021)
- [Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning](https://mlsanity.com/paper/2107.12544/) (2021)
- [SIMA 2: A Generalist Embodied Agent for Virtual Worlds](https://mlsanity.com/paper/2512.04797/) (2025)
- [Few-Shot Bayesian Imitation Learning with Logical Program Policies](https://mlsanity.com/paper/1904.06317/) (2019)
- [Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning](https://mlsanity.com/paper/2111.12990/) (2021)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [PoE-World: Compositional World Modeling with Products of Programmatic Experts](https://mlsanity.com/paper/2505.10819/) (2025)
- [Causal Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.01452/) (2023)
- [Capturing the objects of vision with neural networks](https://mlsanity.com/paper/2109.03351/) (2021)
- [Explore to Generalize in Zero-Shot RL](https://mlsanity.com/paper/2306.03072/) (2023)
- [On the link between conscious function and general intelligence in humans and machines](https://mlsanity.com/paper/2204.05133/) (2022)
- [HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving](https://mlsanity.com/paper/2102.11344/) (2021)
- [Synthesizing world models for bilevel planning](https://mlsanity.com/paper/2503.20124/) (2025)
- [FAIR for AI: An interdisciplinary and international community building perspective](https://mlsanity.com/paper/2210.08973/) (2022)
- [Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation](https://mlsanity.com/paper/2110.04422/) (2021)
- [Discovering User-Interpretable Capabilities of Black-Box Planning Agents](https://mlsanity.com/paper/2107.13668/) (2021)
- [LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations](https://mlsanity.com/paper/1808.07903/) (2018)
- [Conceptual Reinforcement Learning for Language-Conditioned Tasks](https://mlsanity.com/paper/2303.05069/) (2023)
- [OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3](https://mlsanity.com/paper/2607.01531/) (2026)
- [PDSketch: Integrated Planning Domain Programming and Learning](https://mlsanity.com/paper/2303.05501/) (2023)
- [From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks](https://mlsanity.com/paper/2405.15164/) (2024)
- [Object-Category Aware Reinforcement Learning](https://mlsanity.com/paper/2210.07802/) (2022)
- [Granger Causal Interaction Skill Chains](https://mlsanity.com/paper/2306.09509/) (2023)

## Abstract (arXiv)

The recent adaptation of deep neural network-based methods to reinforcement learning and planning domains has yielded remarkable progress on individual tasks. Nonetheless, progress on task-to-task transfer remains limited. In pursuit of efficient and robust generalization, we introduce the Schema Network, an object-oriented generative physics simulator capable of disentangling multiple causes of events and reasoning backward through causes to achieve goals. The richly structured architecture of the Schema Network can learn the dynamics of an environment directly from data. We compare Schema Networks with Asynchronous Advantage Actor-Critic and Progressive Networks on a suite of Breakout variations, reporting results on training efficiency and zero-shot generalization, consistently demonstrating faster, more robust learning and better transfer. We argue that generalizing from limited data and learning causal relationships are essential abilities on the path toward generally intelligent systems.