# Adaptive Skills, Adaptive Partitions (ASAP)

arXiv: https://arxiv.org/abs/1602.03351 · HTML: https://mlsanity.com/paper/1602.03351/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2016.

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

- [Discovery of Options via Meta-Learned Subgoals](https://mlsanity.com/paper/2102.06741/) (2021)
- [When should agents explore?](https://mlsanity.com/paper/2108.11811/) (2021)
- [Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs](https://mlsanity.com/paper/2307.11629/) (2023)
- [Context-Specific Representation Abstraction for Deep Option Learning](https://mlsanity.com/paper/2109.09876/) (2021)
- [Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems](https://mlsanity.com/paper/2507.14850/) (2025)
- [Learning Multi-agent Skills for Tabular Reinforcement Learning using Factor Graphs](https://mlsanity.com/paper/2201.08227/) (2022)
- [Model-Based Reinforcement Learning via Stochastic Hybrid Models](https://mlsanity.com/paper/2111.06211/) (2021)
- [Contrastive Abstraction for Reinforcement Learning](https://mlsanity.com/paper/2410.00704/) (2024)
- [Interpretable Reinforcement Learning Inspired by Piaget's Theory of Cognitive Development](https://mlsanity.com/paper/2102.00572/) (2021)
- [Reusable Options through Gradient-based Meta Learning](https://mlsanity.com/paper/2212.11726/) (2022)
- [An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework](https://mlsanity.com/paper/2305.01322/) (2023)

## Abstract (arXiv)

We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i.e., temporally extended actions or options) as well as (2) where to apply them. We believe that both (1) and (2) are necessary for a truly general skill learning framework, which is a key building block needed to scale up to lifelong learning agents. The ASAP framework can also solve related new tasks simply by adapting where it applies its existing learned skills. We prove that ASAP converges to a local optimum under natural conditions. Finally, our experimental results, which include a RoboCup domain, demonstrate the ability of ASAP to learn where to reuse skills as well as solve multiple tasks with considerably less experience than solving each task from scratch.