mlsanityData to 7 Oct 2026

Learning to Compose Skills

arXiv 1711.11289 ↗First posted 30 Nov 2017cs.AIcited by 15

Not on the map. Why?

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.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 1; 2023: 3; 2024: 1; 2025: 5; 2026: 1.

15 papers.

Sort:

By area:

  1. 2021Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environmentscited by 24
  2. 2021Solving Compositional Reinforcement Learning Problems via Task Reductioncited by 19
  3. 2023Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learningcited by 19
  4. 2021Learning Multi-Objective Curricula for Robotic Policy Learningcited by 3
  5. 2025One Rank at a Time: Cascading Error Dynamics in Sequential Learningcited by 3
  6. 2021Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchiescited by 2
  7. 2024I Know How: Combining Prior Policies to Solve New Taskscited by 2
  8. 2025Foundations of a Developmental Design Paradigm for Integrated Continual Learning, Deliberative Behavior, and Comprehensibilitycited by 2
  9. 2023A Constrained-Optimization Approach to the Execution of Prioritized Stacks of Learned Multi-Robot Taskscited by 1
  10. 2023Towards Zero-Shot Functional Compositionality of Language Modelscited by 1
  11. 2025On the Parallels Between Evolutionary Theory and the State of AIcited by 1
  12. 2022Soft Actor-Critic with Inhibitory Networks for Faster Retrainingcited by 0
3 more
  1. 2025Multi-CALF: A Policy Combination Approach with Statistical Guaranteescited by 0
  2. 2025Evolutionary Developmental Biology Can Serve as the Conceptual Foundation for a New Design Paradigm in Artificial Intelligencecited by 0
  3. 2026Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Modelscited by 0