mlsanityData to 7 Oct 2026

Measuring Interventional Robustness in Reinforcement Learning

arXiv 2209.09058 ↗First posted 19 Sep 2022cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent work in reinforcement learning has focused on several characteristics of learned policies that go beyond maximizing reward. These properties include fairness, explainability, generalization, and robustness. In this paper, we define interventional robustness (IR), a measure of how much variability is introduced into learned policies by incidental aspects of the training procedure, such as the order of training data or the particular exploratory actions taken by agents. A training procedure has high IR when the agents it produces take very similar actions under intervention, despite variation in these incidental aspects of the training procedure. We develop an intuitive, quantitative measure of IR and calculate it for eight algorithms in three Atari environments across dozens of interventions and states. From these experiments, we find that IR varies with the amount of training and type of algorithm and that high performance does not imply high IR, as one might expect.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 53 references that are in the map. First posted on arXiv 19 Sep 2022.

Builds on

27 of 53 references.

References · 27

  1. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  2. 2017Deep Reinforcement Learning that Matterscited by 727
  3. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  4. 2015Policy Distillationcited by 414
  5. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  6. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
  7. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  8. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  9. 2018Programmatically Interpretable Reinforcement Learningcited by 192
  10. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  11. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 170
  12. 2020Explainable Reinforcement Learning: A Surveycited by 139
15 more
  1. 2018Assessing Generalization in Deep Reinforcement Learningcited by 132
  2. 2017Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Controlcited by 92
  3. 2019Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learningcited by 60
  4. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
  5. 2019Measuring the Reliability of Reinforcement Learning Algorithmscited by 49
  6. 2018Contrastive Explanations for Reinforcement Learning in terms of Expected Consequencescited by 44
  7. 2021Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learningcited by 38
  8. 2018Stability-certified reinforcement learning: A control-theoretic perspectivecited by 29
  9. 2019Online Robustness Training for Deep Reinforcement Learningcited by 26
  10. 2019Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learningcited by 23
  11. 2018Measuring and Characterizing Generalization in Deep Reinforcement Learningcited by 20
  12. 2019Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environmentscited by 9
  13. 2017A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loopcited by 7
  14. 2021Explainable Artificial Intelligence (XAI) for Increasing User Trust in Deep Reinforcement Learning Driven Autonomous Systemscited by 7
  15. 2018ToyBox: Better Atari Environments for Testing Reinforcement Learning Agentscited by 2

Built on by

Not cited yet.