# Auditing Robot Learning for Safety and Compliance during Deployment

arXiv: https://arxiv.org/abs/2110.05702 · HTML: https://mlsanity.com/paper/2110.05702/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 12 Oct 2021.

## Builds on (most cited first, 25 of 25)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Exploring Generalization in Deep Learning](https://mlsanity.com/paper/1706.08947/) (2017)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://mlsanity.com/paper/1705.08551/) (2017)
- [Learning to Drive in a Day](https://mlsanity.com/paper/1807.00412/) (2018)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances](https://mlsanity.com/paper/1709.07523/) (2017)
- [Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones](https://mlsanity.com/paper/2010.15920/) (2020)
- [Learning-based Model Predictive Control for Safe Exploration](https://mlsanity.com/paper/1803.08287/) (2018)
- [Learning to be Safe: Deep RL with a Safety Critic](https://mlsanity.com/paper/2010.14603/) (2020)
- [Conservative Safety Critics for Exploration](https://mlsanity.com/paper/2010.14497/) (2020)
- [Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost](https://mlsanity.com/paper/1810.06045/) (2018)
- [Consequences of Misaligned AI](https://mlsanity.com/paper/2102.03896/) (2021)
- [Shared Autonomy via Deep Reinforcement Learning](https://mlsanity.com/paper/1802.01744/) (2018)
- [NeurIPS 2020 Competition: Predicting Generalization in Deep Learning](https://mlsanity.com/paper/2012.07976/) (2020)
- [Generalization bounds for deep learning](https://mlsanity.com/paper/2012.04115/) (2020)
- [Should Robots be Obedient?](https://mlsanity.com/paper/1705.09990/) (2017)
- [Learning under Misspecified Objective Spaces](https://mlsanity.com/paper/1810.05157/) (2018)
- [Reachability-Based Safety Guarantees using Efficient Initializations](https://mlsanity.com/paper/1903.07715/) (2019)
- [Auditing AI models for Verified Deployment under Semantic Specifications](https://mlsanity.com/paper/2109.12456/) (2021)

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

- [SafeMimic: Towards Safe and Autonomous Human-to-Robot Imitation for Mobile Manipulation](https://mlsanity.com/paper/2506.15847/) (2025)
- [MLOps Spanning Whole Machine Learning Life Cycle: A Survey](https://mlsanity.com/paper/2304.07296/) (2023)
- [Passivity-Centric Safe Reinforcement Learning for Contact-Rich Robotic Tasks](https://mlsanity.com/paper/2503.00287/) (2025)
- [EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems](https://mlsanity.com/paper/2604.11174/) (2026)

## Abstract (arXiv)

Robots of the future are going to exhibit increasingly human-like and super-human intelligence in a myriad of different tasks. They are also likely going to fail and be incompliant with human preferences in increasingly subtle ways. Towards the goal of achieving autonomous robots, the robot learning community has made rapid strides in applying machine learning techniques to train robots through data and interaction. This makes the study of how best to audit these algorithms for checking their compatibility with humans, pertinent and urgent. In this paper, we draw inspiration from the AI Safety and Alignment communities and make the case that we need to urgently consider ways in which we can best audit our robot learning algorithms to check for failure modes, and ensure that when operating autonomously, they are indeed behaving in ways that the human algorithm designers intend them to. We believe that this is a challenging problem that will require efforts from the entire robot learning community, and do not attempt to provide a concrete framework for auditing. Instead, we outline high-level guidance and a possible approach towards formulating this framework which we hope will serve as a useful starting point for thinking about auditing in the context of robot learning.