mlsanityData to 7 Oct 2026

Risk-Aware Active Inverse Reinforcement Learning

arXiv 1901.02161 ↗First posted 8 Jan 2019cs.LG stat.MLcited by 26

On the map: Offline RL and imitation learning from data → Inverse reinforcement learning

Abstract (arXiv)

Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. Utilizing recent advances in performance bounds for inverse reinforcement learning, we propose a risk-aware active inverse reinforcement learning algorithm that focuses active queries on areas of the state space with the potential for large generalization error. We show that risk-aware active learning outperforms standard active IRL approaches on gridworld, simulated driving, and table setting tasks, while also providing a performance-based stopping criterion that allows a robot to know when it has received enough demonstrations to safely perform a task.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 7 of its 24 references that are in the map. First posted on arXiv 8 Jan 2019.

Builds on

7 of 24 references.

References · 7

  1. 2017Deep reinforcement learning from human preferencescited by 3,846
  2. 2016Concrete Problems in AI Safetycited by 1,582
  3. 2015Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approachcited by 162
  4. 2017Interactive Learning from Policy-Dependent Human Feedbackcited by 155
  5. 2014Optimizing the CVaR via Samplingcited by 98
  6. 2017Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learningcited by 17
  7. 2017On Ensuring that Intelligent Machines Are Well-Behavedcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 2; 2020: 3; 2021: 4; 2022: 8; 2023: 4; 2024: 2; 2025: 1; 2026: 2.

26 papers.

Sort:

By area:

  1. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferencescited by 73
  2. 2020Bayesian Robust Optimization for Imitation Learningcited by 28
  3. 2022Active Exploration for Inverse Reinforcement Learningcited by 27
  4. 2019Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraintscited by 18
  5. 2022Inducing Structure in Reward Learning by Learning Featurescited by 16
  6. 2022End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functionscited by 10
  7. 2022Time-Efficient Reward Learning via Visually Assisted Cluster Rankingcited by 8
  8. 2023BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Taskscited by 8
  9. 2019Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrationscited by 5
  10. 2021Automatic Risk Adaptation in Distributional Reinforcement Learningcited by 5
  11. 2021Assisted Robust Reward Designcited by 5
  12. 2021Fully General Online Imitation Learningcited by 4
14 more
  1. 2022Environment Design for Inverse Reinforcement Learningcited by 4
  2. 2022Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planningcited by 3
  3. 2023Learning Formal Specifications from Membership and Preference Queriescited by 3
  4. 2022Learning from Physical Human Feedback: An Object-Centric One-Shot Adaptation Methodcited by 2
  5. 2024Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocauterycited by 2
  6. 2024RL, but don't do anything I wouldn't docited by 2
  7. 2021Neural Task Success Classifiers for Robotic Manipulation from Few Real Demonstrationscited by 1
  8. 2025PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learningcited by 1
  9. 2020Preventing Imitation Learning with Adversarial Policy Ensemblescited by 0
  10. 2022MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigationcited by 0
  11. 2023Imitating careful experts to avoid catastrophic eventscited by 0
  12. 2023Interactively Teaching an Inverse Reinforcement Learner with Limited Feedbackcited by 0
  13. 2026Learning Safe Agent Behaviour from Human Preferences and Justifications via World Modelscited by 0
  14. 2026Q-based Variational Inverse Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2019Active Learning for Risk-Sensitive Inverse Reinforcement Learning
  2. 2022Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning
  3. 2024Toward Information Theoretic Active Inverse Reinforcement Learning
  4. 2018A Framework and Method for Online Inverse Reinforcement Learning
  5. 2022Safe Inverse Reinforcement Learning via Control Barrier Function
  6. 2022Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations
  7. 2023BC-IRL: Learning Generalizable Reward Functions from Demonstrations
  8. 2018Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications