# Supervised Bayesian Specification Inference from Demonstrations

arXiv: https://arxiv.org/abs/2107.02912 · HTML: https://mlsanity.com/paper/2107.02912/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 78 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [Inverse Reward Design](https://mlsanity.com/paper/1711.02827/) (2017)
- [Reinforcement Learning With Temporal Logic Rewards](https://mlsanity.com/paper/1612.03471/) (2016)
- [Learning from Suboptimal Demonstration via Self-Supervised Reward Regression](https://mlsanity.com/paper/2010.11723/) (2020)
- [Learning to Infer Graphics Programs from Hand-Drawn Images](https://mlsanity.com/paper/1707.09627/) (2017)
- [Environment-Independent Task Specifications via GLTL](https://mlsanity.com/paper/1704.04341/) (2017)
- [Few-Shot Bayesian Imitation Learning with Logical Program Policies](https://mlsanity.com/paper/1904.06317/) (2019)
- [A Theory of Formal Synthesis via Inductive Learning](https://mlsanity.com/paper/1505.03953/) (2015)
- [Specification Patterns for Robotic Missions](https://mlsanity.com/paper/1901.02077/) (2019)
- [Interpretable Apprenticeship Learning with Temporal Logic Specifications](https://mlsanity.com/paper/1710.10532/) (2017)
- [Information-Guided Temporal Logic Inference with Prior Knowledge](https://mlsanity.com/paper/1811.08846/) (2018)
- [The State of Industrial Robotics: Emerging Technologies, Challenges, and Key Research Directions](https://mlsanity.com/paper/2010.14537/) (2020)
- [Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments](https://mlsanity.com/paper/1808.00349/) (2018)

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

- [Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planning](https://mlsanity.com/paper/2508.08983/) (2025)

## Abstract (arXiv)

When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD) has failed to capture this notion of the acceptability of a task's execution; meanwhile, temporal logics provide a flexible language for expressing task specifications. Inspired by this, we present Bayesian specification inference, a probabilistic model for inferring task specification as a temporal logic formula. We incorporate methods from probabilistic programming to define our priors, along with a domain-independent likelihood function to enable sampling-based inference. We demonstrate the efficacy of our model for inferring specifications, with over 90% similarity observed between the inferred specification and the ground truth, both within a synthetic domain and during a real-world table setting task.