# Policy Compatible Skill Incremental Learning via Lazy Learning Interface

arXiv: https://arxiv.org/abs/2509.20612 · HTML: https://mlsanity.com/paper/2509.20612/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 80 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 30 of 62)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [Dynamics-Aware Unsupervised Discovery of Skills](https://mlsanity.com/paper/1907.01657/) (2019)
- [Orthogonal Subspace Learning for Language Model Continual Learning](https://mlsanity.com/paper/2310.14152/) (2023)
- [Variational Intrinsic Control](https://mlsanity.com/paper/1611.07507/) (2016)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [Accelerating Reinforcement Learning with Learned Skill Priors](https://mlsanity.com/paper/2010.11944/) (2020)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [Learning Attentional Communication for Multi-Agent Cooperation](https://mlsanity.com/paper/1805.07733/) (2018)
- [Continual Learning with Pre-Trained Models: A Survey](https://mlsanity.com/paper/2401.16386/) (2024)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [Uncertainty-based Continual Learning with Adaptive Regularization](https://mlsanity.com/paper/1905.11614/) (2019)
- [Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA](https://mlsanity.com/paper/2304.06027/) (2023)
- [A Definition of Continual Reinforcement Learning](https://mlsanity.com/paper/2307.11046/) (2023)
- [Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation](https://mlsanity.com/paper/2109.13841/) (2021)
- [Open-Endedness is Essential for Artificial Superhuman Intelligence](https://mlsanity.com/paper/2406.04268/) (2024)

## Built on by (most cited first, 3 of 3)

- [Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning](https://mlsanity.com/paper/2606.15685/) (2026)
- [LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective](https://mlsanity.com/paper/2606.26183/) (2026)
- [Test-time Multi-agent Coordination by Decomposed Value Gradient Flow](https://mlsanity.com/paper/2610.02554/) (2026)

## Abstract (arXiv)

Skill Incremental Learning (SIL) is the process by which an embodied agent expands and refines its skill set over time by leveraging experience gained through interaction with its environment or by the integration of additional data. SIL facilitates efficient acquisition of hierarchical policies grounded in reusable skills for downstream tasks. However, as the skill repertoire evolves, it can disrupt compatibility with existing skill-based policies, limiting their reusability and generalization. In this work, we propose SIL-C, a novel framework that ensures skill-policy compatibility, allowing improvements in incrementally learned skills to enhance the performance of downstream policies without requiring policy re-training or structural adaptation. SIL-C employs a bilateral lazy learning-based mapping technique to dynamically align the subtask space referenced by policies with the skill space decoded into agent behaviors. This enables each subtask, derived from the policy's decomposition of a complex task, to be executed by selecting an appropriate skill based on trajectory distribution similarity. We evaluate SIL-C across diverse SIL scenarios and demonstrate that it maintains compatibility between evolving skills and downstream policies while ensuring efficiency throughout the learning process.