# Safe Inverse Reinforcement Learning via Control Barrier Function

arXiv: https://arxiv.org/abs/2212.02753 · HTML: https://mlsanity.com/paper/2212.02753/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Placed in

- Offline RL and imitation learning from data / [Safe offline RL](https://mlsanity.com/offlinerl/safe-offline-rl/)

## Builds on (most cited first, 23 of 23)

- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [Emergence of Locomotion Behaviours in Rich Environments](https://mlsanity.com/paper/1707.02286/) (2017)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [Learning Control Barrier Functions from Expert Demonstrations](https://mlsanity.com/paper/2004.03315/) (2020)
- [Learning from Suboptimal Demonstration via Self-Supervised Reward Regression](https://mlsanity.com/paper/2010.11723/) (2020)
- [Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates](https://mlsanity.com/paper/2101.05436/) (2021)
- [Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences](https://mlsanity.com/paper/2002.09089/) (2020)
- [Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions](https://mlsanity.com/paper/2004.07584/) (2020)
- [Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations](https://mlsanity.com/paper/2108.01846/) (2021)
- [Deep Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1811.11329/) (2018)
- [Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach](https://mlsanity.com/paper/2003.04950/) (2020)
- [Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function](https://mlsanity.com/paper/2103.01556/) (2021)
- [Deep Bayesian Reward Learning from Preferences](https://mlsanity.com/paper/1912.04472/) (2019)
- [Learning Hybrid Control Barrier Functions from Data](https://mlsanity.com/paper/2011.04112/) (2020)
- [Navigating Occluded Intersections with Autonomous Vehicles using Deep Reinforcement Learning](https://mlsanity.com/paper/1705.01196/) (2017)
- [Cooperative and Distributed Reinforcement Learning of Drones for Field Coverage](https://mlsanity.com/paper/1803.07250/) (2018)
- [Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation](https://mlsanity.com/paper/2001.00503/) (2020)
- [Autonomous Braking System via Deep Reinforcement Learning](https://mlsanity.com/paper/1702.02302/) (2017)
- [Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning](https://mlsanity.com/paper/1707.00724/) (2017)
- [Feature Analysis and Selection for Training an End-to-End Autonomous Vehicle Controller Using the Deep Learning Approach](https://mlsanity.com/paper/1703.09744/) (2017)

## Built on by (most cited first, 3 of 3)

- [ARCADE: Scalable Demonstration Collection and Generation via Augmented Reality for Imitation Learning](https://mlsanity.com/paper/2410.15994/) (2024)
- [InvThink: Premortem Reasoning for Safer Language Models](https://mlsanity.com/paper/2510.01569/) (2025)
- [Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation](https://mlsanity.com/paper/2607.13938/) (2026)

## Abstract (arXiv)

Learning from Demonstration (LfD) is a powerful method for enabling robots to perform novel tasks as it is often more tractable for a non-roboticist end-user to demonstrate the desired skill and for the robot to efficiently learn from the associated data than for a human to engineer a reward function for the robot to learn the skill via reinforcement learning (RL). Safety issues arise in modern LfD techniques, e.g., Inverse Reinforcement Learning (IRL), just as they do for RL; yet, safe learning in LfD has received little attention. In the context of agile robots, safety is especially vital due to the possibility of robot-environment collision, robot-human collision, and damage to the robot. In this paper, we propose a safe IRL framework, CBFIRL, that leverages the Control Barrier Function (CBF) to enhance the safety of the IRL policy. The core idea of CBFIRL is to combine a loss function inspired by CBF requirements with the objective in an IRL method, both of which are jointly optimized via gradient descent. In the experiments, we show our framework performs safer compared to IRL methods without CBF, that is ~15% and ~20% improvement for two levels of difficulty of a 2D racecar domain and ~ 50% improvement for a 3D drone domain.