mlsanityData to 14 Oct 2026

Supervised Bayesian Specification Inference from Demonstrations

arXiv 2107.02912 ↗First posted 6 Jul 2021cs.AI cs.LG cs.ROcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

14 of 78 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 260
  3. 2017Inverse Reward Designcited by 249
  4. 2016Reinforcement Learning With Temporal Logic Rewardscited by 117
  5. 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regressioncited by 84
  6. 2017Learning to Infer Graphics Programs from Hand-Drawn Imagescited by 74
  7. 2017Environment-Independent Task Specifications via GLTLcited by 67
  8. 2019Few-Shot Bayesian Imitation Learning with Logical Program Policiescited by 30
  9. 2015A Theory of Formal Synthesis via Inductive Learningcited by 17
  10. 2019Specification Patterns for Robotic Missionscited by 16
  11. 2017Interpretable Apprenticeship Learning with Temporal Logic Specificationscited by 13
  12. 2018Information-Guided Temporal Logic Inference with Prior Knowledgecited by 13
2 more
  1. 2020The State of Industrial Robotics: Emerging Technologies, Challenges, and Key Research Directionscited by 7
  2. 2018Learning Generalizable Robot Skills from Demonstrations in Cluttered Environmentscited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Learning Task Specifications from Demonstrations as Probabilistic Automata
  2. 2020Elaborating on Learned Demonstrations with Temporal Logic Specifications
  3. 2022Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments
  4. 2021Learning from Demonstrations using Signal Temporal Logic
  5. 2026Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming
  6. 2019Inferring Personalized Bayesian Embeddings for Learning from Heterogeneous Demonstration
  7. 2022Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
  8. 2019Maximum Causal Entropy Specification Inference from Demonstrations