# SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning

arXiv: https://arxiv.org/abs/2205.03130 · HTML: https://mlsanity.com/paper/2205.03130/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 6 May 2022.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 15 of 15)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Variational Inference of Disentangled Latent Concepts from Unlabeled Observations](https://mlsanity.com/paper/1711.00848/) (2017)
- [Distral: Robust Multitask Reinforcement Learning](https://mlsanity.com/paper/1707.04175/) (2017)
- [Modular Multitask Reinforcement Learning with Policy Sketches](https://mlsanity.com/paper/1611.01796/) (2016)
- [Diagnosing and Enhancing VAE Models](https://mlsanity.com/paper/1903.05789/) (2019)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning](https://mlsanity.com/paper/1706.05064/) (2017)
- [Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning](https://mlsanity.com/paper/1712.07294/) (2017)
- [Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions](https://mlsanity.com/paper/1812.09502/) (2018)
- [NestedVAE: Isolating Common Factors via Weak Supervision](https://mlsanity.com/paper/2002.11576/) (2020)
- [Hyperprior Induced Unsupervised Disentanglement of Latent Representations](https://mlsanity.com/paper/1809.04497/) (2018)
- [Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement](https://mlsanity.com/paper/1911.06443/) (2019)
- [Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour](https://mlsanity.com/paper/2106.01434/) (2021)

## Built on by (most cited first, 4 of 4)

- [Multi-task Hierarchical Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/2305.12633/) (2023)
- [PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining](https://mlsanity.com/paper/2303.08789/) (2023)
- [Generalizing to New Tasks via One-Shot Compositional Subgoals](https://mlsanity.com/paper/2205.07716/) (2022)
- [Shared-unique Features and Task-aware Prioritized Sampling on Multi-task Reinforcement Learning](https://mlsanity.com/paper/2406.00761/) (2024)

## Abstract (arXiv)

In this work, we introduce a new perspective for learning transferable content in multi-task imitation learning. Humans are able to transfer skills and knowledge. If we can cycle to work and drive to the store, we can also cycle to the store and drive to work. We take inspiration from this and hypothesize the latent memory of a policy network can be disentangled into two partitions. These contain either the knowledge of the environmental context for the task or the generalizable skill needed to solve the task. This allows improved training efficiency and better generalization over previously unseen combinations of skills in the same environment, and the same task in unseen environments. We used the proposed approach to train a disentangled agent for two different multi-task IL environments. In both cases we out-performed the SOTA by 30% in task success rate. We also demonstrated this for navigation on a real robot.