mlsanityData to 14 Oct 2026

Active Constraint Learning in High Dimensions from Demonstrations

arXiv 2512.22757 ↗First posted 28 Dec 2025cs.RO cs.AI cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Robot learning from demonstration

Abstract (arXiv)

We present an iterative active constraint learning (ACL) algorithm, within the learning from demonstrations (LfD) paradigm, which intelligently solicits informative demonstration trajectories for inferring an unknown constraint in the demonstrator's environment. Our approach iteratively trains a Gaussian process (GP) on the available demonstration dataset to represent the unknown constraints, uses the resulting GP posterior to query start/goal states, and generates informative demonstrations which are added to the dataset. Across simulation and hardware experiments using high-dimensional nonlinear dynamics and unknown nonlinear constraints, our method outperforms a baseline, random-sampling based method at accurately performing constraint inference from an iteratively generated set of sparse but informative demonstrations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data. Builds on 13 of its 27 references that are in the map. First posted on arXiv 28 Dec 2025.

Builds on

13 of 27 references.

References · 13

  1. 2021PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingcited by 302
  2. 2020Efficiently Sampling Functions from Gaussian Process Posteriorscited by 127
  3. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  4. 2021Maximum Likelihood Constraint Inference from Stochastic Demonstrationscited by 15
  5. 2017Risk-sensitive Inverse Reinforcement Learning via Semi- and Non-Parametric Methodscited by 12
  6. 2020Learning Constraints from Locally-Optimal Demonstrations under Cost Function Uncertaintycited by 12
  7. 2019Learning Parametric Constraints in High Dimensions from Demonstrationscited by 10
  8. 2020Uncertainty-Aware Constraint Learning for Adaptive Safe Motion Planning from Demonstrationscited by 10
  9. 2022Active Uncertainty Reduction for Human-Robot Interaction: An Implicit Dual Control Approachcited by 10
  10. 2021Gaussian Process Constraint Learning for Scalable Chance-Constrained Motion Planning from Demonstrationscited by 6
  11. 2024Bayesian Constraint Inference from User Demonstrations Based on Margin-Respecting Preference Modelscited by 4
  12. 2024Intent Demonstration in General-Sum Dynamic Games via Iterative Linear-Quadratic Approximationscited by 3
1 more
  1. 2023Constraint Inference in Control Tasks from Expert Demonstrations via Inverse Optimizationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2018Learning Constraints from Demonstrations
  2. 2026Learning Unknown Constraints without Unsafe Data via Optimality and Counterfactual Regularization
  3. 2025When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
  4. 2024Jointly Learning Cost and Constraints from Demonstrations for Safe Trajectory Generation
  5. 2026Learning from Demonstration via Spatiotemporal Tubes for Unknown Euler-Lagrange Systems
  6. 2021Learning from Successful and Failed Demonstrations via Optimization
  7. 2025ZORMS-LfD: Learning from Demonstrations with Zeroth-Order Random Matrix Search
  8. 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regression