# Learning to Compose Skills

arXiv: https://arxiv.org/abs/1711.11289 · HTML: https://mlsanity.com/paper/1711.11289/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2017.

## Built on by (most cited first, 15 of 15)

- [Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments](https://mlsanity.com/paper/2201.00042/) (2021)
- [Solving Compositional Reinforcement Learning Problems via Task Reduction](https://mlsanity.com/paper/2103.07607/) (2021)
- [Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning](https://mlsanity.com/paper/2305.18869/) (2023)
- [Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies](https://mlsanity.com/paper/2110.01833/) (2021)
- [Learning Multi-Objective Curricula for Robotic Policy Learning](https://mlsanity.com/paper/2110.03032/) (2021)
- [One Rank at a Time: Cascading Error Dynamics in Sequential Learning](https://mlsanity.com/paper/2505.22602/) (2025)
- [I Know How: Combining Prior Policies to Solve New Tasks](https://mlsanity.com/paper/2406.09835/) (2024)
- [Foundations of a Developmental Design Paradigm for Integrated Continual Learning, Deliberative Behavior, and Comprehensibility](https://mlsanity.com/paper/2502.13935/) (2025)
- [A Constrained-Optimization Approach to the Execution of Prioritized Stacks of Learned Multi-Robot Tasks](https://mlsanity.com/paper/2301.05346/) (2023)
- [Towards Zero-Shot Functional Compositionality of Language Models](https://mlsanity.com/paper/2303.03103/) (2023)
- [On the Parallels Between Evolutionary Theory and the State of AI](https://mlsanity.com/paper/2505.23774/) (2025)
- [Soft Actor-Critic with Inhibitory Networks for Faster Retraining](https://mlsanity.com/paper/2202.02918/) (2022)
- [Multi-CALF: A Policy Combination Approach with Statistical Guarantees](https://mlsanity.com/paper/2505.12350/) (2025)
- [Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligence](https://mlsanity.com/paper/2506.12891/) (2025)
- [Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models](https://mlsanity.com/paper/2608.24042/) (2026)

## Abstract (arXiv)

We present a differentiable framework capable of learning a wide variety of compositions of simple policies that we call skills. By recursively composing skills with themselves, we can create hierarchies that display complex behavior. Skill networks are trained to generate skill-state embeddings that are provided as inputs to a trainable composition function, which in turn outputs a policy for the overall task. Our experiments on an environment consisting of multiple collect and evade tasks show that this architecture is able to quickly build complex skills from simpler ones. Furthermore, the learned composition function displays some transfer to unseen combinations of skills, allowing for zero-shot generalizations.