# Learning Parameterized Skills from Demonstrations

arXiv: https://arxiv.org/abs/2510.24095 · HTML: https://mlsanity.com/paper/2510.24095/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [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)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Learning by Playing - Solving Sparse Reward Tasks from Scratch](https://mlsanity.com/paper/1802.10567/) (2018)
- [Toward the Fundamental Limits of Imitation Learning](https://mlsanity.com/paper/2009.05990/) (2020)
- [The Option Keyboard: Combining Skills in Reinforcement Learning](https://mlsanity.com/paper/2106.13105/) (2021)
- [LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery](https://mlsanity.com/paper/2311.02058/) (2023)
- [Reinforcement Learning with Parameterized Actions](https://mlsanity.com/paper/1509.01644/) (2015)
- [Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space](https://mlsanity.com/paper/1810.06394/) (2018)
- [Learning Robot Skills with Temporal Variational Inference](https://mlsanity.com/paper/2006.16232/) (2020)
- [Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings](https://mlsanity.com/paper/1806.02813/) (2018)
- [DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrations](https://mlsanity.com/paper/1710.05421/) (2017)
- [Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information](https://mlsanity.com/paper/1810.01266/) (2018)
- [Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives](https://mlsanity.com/paper/1906.10667/) (2019)
- [Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies](https://mlsanity.com/paper/2112.05062/) (2021)
- [Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces](https://mlsanity.com/paper/1905.04388/) (2019)
- [Learning Options via Compression](https://mlsanity.com/paper/2212.04590/) (2022)
- [PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control](https://mlsanity.com/paper/2402.10450/) (2024)
- [Composing Task-Agnostic Policies with Deep Reinforcement Learning](https://mlsanity.com/paper/1905.10681/) (2019)
- [EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data](https://mlsanity.com/paper/2406.17768/) (2024)
- [Language-guided Skill Learning with Temporal Variational Inference](https://mlsanity.com/paper/2402.16354/) (2024)
- [Model-based Reinforcement Learning for Parameterized Action Spaces](https://mlsanity.com/paper/2404.03037/) (2024)
- [Meta-Learning Parameterized Skills](https://mlsanity.com/paper/2206.03597/) (2022)

## Built on by (most cited first, 1 of 1)

- [From Noise to Control: Parameterized Diffusion Policies](https://mlsanity.com/paper/2606.00336/) (2026)

## Abstract (arXiv)

We present DEPS, an end-to-end algorithm for discovering parameterized skills from expert demonstrations. Our method learns parameterized skill policies jointly with a meta-policy that selects the appropriate discrete skill and continuous parameters at each timestep. Using a combination of temporal variational inference and information-theoretic regularization methods, we address the challenge of degeneracy common in latent variable models, ensuring that the learned skills are temporally extended, semantically meaningful, and adaptable. We empirically show that learning parameterized skills from multitask expert demonstrations significantly improves generalization to unseen tasks. Our method outperforms multitask as well as skill learning baselines on both LIBERO and MetaWorld benchmarks. We also demonstrate that DEPS discovers interpretable parameterized skills, such as an object grasping skill whose continuous arguments define the grasp location.