# Sample-Efficient Expert Query Control in Active Imitation Learning via Conformal Prediction

arXiv: https://arxiv.org/abs/2512.00453 · HTML: https://mlsanity.com/paper/2512.00453/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 13 of its 17 references that are in the map.
- First posted on arXiv 29 Nov 2025.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 13 of 13)

- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Model-Based Imitation Learning for Urban Driving](https://mlsanity.com/paper/2210.07729/) (2022)
- [ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning](https://mlsanity.com/paper/2109.08273/) (2021)
- [EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning](https://mlsanity.com/paper/1807.08364/) (2018)
- [Query-Efficient Imitation Learning for End-to-End Autonomous Driving](https://mlsanity.com/paper/1605.06450/) (2016)
- [LazyDAgger: Reducing Context Switching in Interactive Imitation Learning](https://mlsanity.com/paper/2104.00053/) (2021)
- [Surgical Robot Transformer (SRT): Imitation Learning for Surgical Tasks](https://mlsanity.com/paper/2407.12998/) (2024)
- [Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision](https://mlsanity.com/paper/2206.14349/) (2022)
- [Formal Verification and Control with Conformal Prediction](https://mlsanity.com/paper/2409.00536/) (2024)
- [Comparing Human-Centric and Robot-Centric Sampling for Robot Deep Learning from Demonstrations](https://mlsanity.com/paper/1610.00850/) (2016)
- [Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback](https://mlsanity.com/paper/2410.08852/) (2024)
- [Efficient Active Imitation Learning with Random Network Distillation](https://mlsanity.com/paper/2411.01894/) (2024)

## Abstract (arXiv)

Active imitation learning (AIL) combats covariate shift by querying an expert during training. However, expert action labeling often dominates the cost, especially in GPU-intensive simulators, human-in-the-loop settings, and robot fleets that revisit near-duplicate states. We present Conformalized Rejection Sampling for Active Imitation Learning (CRSAIL), a querying rule that requests an expert action only when the visited state is under-represented in the expert-labeled dataset. CRSAIL scores state novelty by the distance to the K-th nearest expert state and sets a single global threshold via conformal prediction. This threshold is the empirical (1-α) quantile of on-policy calibration scores, providing a distribution-free calibration rule that links α to the expected query rate and makes α a task-agnostic tuning knob. This state-space querying strategy is robust to outliers and, unlike safety-gate-based AIL, can be run without real-time expert takeovers: we roll out full trajectories (episodes) with the learner and only afterward query the expert on a subset of visited states. Evaluated on MuJoCo robotics tasks, CRSAIL matches or exceeds expert-level reward while reducing total expert queries by up to 96% vs. DAgger and up to 65% vs. prior AIL methods, with empirical robustness to α and K, easing deployment on novel systems with unknown dynamics.