# Deep Probabilistic Movement Primitives with a Bayesian Aggregator

arXiv: https://arxiv.org/abs/2307.05141 · HTML: https://mlsanity.com/paper/2307.05141/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 11 Jul 2023.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Neural Processes](https://mlsanity.com/paper/1807.01622/) (2018)
- [Neural Dynamic Policies for End-to-End Sensorimotor Learning](https://mlsanity.com/paper/2012.02788/) (2020)
- [Resampled Priors for Variational Autoencoders](https://mlsanity.com/paper/1810.11428/) (2018)
- [Learning Robot Skills with Temporal Variational Inference](https://mlsanity.com/paper/2006.16232/) (2020)
- [Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information](https://mlsanity.com/paper/1810.01266/) (2018)
- [Hierarchical Neural Dynamic Policies](https://mlsanity.com/paper/2107.05627/) (2021)
- [Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills](https://mlsanity.com/paper/2010.13766/) (2020)

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

- [Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning](https://mlsanity.com/paper/2401.11437/) (2024)
- [Conditional Variational Auto Encoder Based Dynamic Motion for Multi-task Imitation Learning](https://mlsanity.com/paper/2405.15266/) (2024)
- [TamedPUMA: safe and stable imitation learning with geometric fabrics](https://mlsanity.com/paper/2503.17432/) (2025)
- [Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models](https://mlsanity.com/paper/2605.11809/) (2026)

## Abstract (arXiv)

Movement primitives are trainable parametric models that reproduce robotic movements starting from a limited set of demonstrations. Previous works proposed simple linear models that exhibited high sample efficiency and generalization power by allowing temporal modulation of movements (reproducing movements faster or slower), blending (merging two movements into one), via-point conditioning (constraining a movement to meet some particular via-points) and context conditioning (generation of movements based on an observed variable, e.g., position of an object). Previous works have proposed neural network-based motor primitive models, having demonstrated their capacity to perform tasks with some forms of input conditioning or time-modulation representations. However, there has not been a single unified deep motor primitive's model proposed that is capable of all previous operations, limiting neural motor primitive's potential applications. This paper proposes a deep movement primitive architecture that encodes all the operations above and uses a Bayesian context aggregator that allows a more sound context conditioning and blending. Our results demonstrate our approach can scale to reproduce complex motions on a larger variety of input choices compared to baselines while maintaining operations of linear movement primitives provide.