mlsanityData to 7 Oct 2026

Explaining Imitation Learning through Frames

arXiv 2301.01088 ↗First posted 3 Jan 2023cs.LG cs.CVcited by 1

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

As one of the prevalent methods to achieve automation systems, Imitation Learning (IL) presents a promising performance in a wide range of domains. However, despite the considerable improvement in policy performance, the corresponding research on the explainability of IL models is still limited. Inspired by the recent approaches in explainable artificial intelligence methods, we proposed a model-agnostic explaining framework for IL models called R2RISE. R2RISE aims to explain the overall policy performance with respect to the frames in demonstrations. It iteratively retrains the black-box IL model from the randomized masked demonstrations and uses the conventional evaluation outcome environment returns as the coefficient to build an importance map. We also conducted experiments to investigate three major questions concerning frames' importance equality, the effectiveness of the importance map, and connections between importance maps from different IL models. The result shows that R2RISE successfully distinguishes important frames from the demonstrations.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 18 of its 31 references that are in the map. First posted on arXiv 3 Jan 2023.

Builds on

18 of 31 references.

Closest ancestors · 4

Same direction, newest first

  1. 2021Imitation Learning: Progress, Taxonomies and Challenges23 Jun
  2. 2020Modelling Agent Policies with Interpretable Imitation Learning19 Jun
  3. 2019Causal Confusion in Imitation Learning28 May
  4. 2018Behavioral Cloning from Observation4 May

Other references · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2016OpenAI Gymcited by 1,684
  4. 2016Generative Adversarial Imitation Learningcited by 1,576
  5. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  6. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  7. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  8. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  9. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
  10. 2018One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learningcited by 146
  11. 2017Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learningcited by 77
  12. 2020Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraftcited by 15
2 more
  1. 2021Explainable Hierarchical Imitation Learning for Robotic Drink Pouringcited by 11
  2. 2022Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Symbolic Imitation Learning: From Black-Box to Explainable Driving Policiescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planning
  2. 2020Causal Transfer for Imitation Learning and Decision Making under Sensor-shift
  3. 2026Rethinking Demonstration Unlearning in Imitation Learning for Robotics
  4. 2024Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
  5. 2022Imitation Learning by Estimating Expertise of Demonstrators
  6. 2026Human-to-Robot Interaction: Learning from Video Demonstration for Robot Imitation
  7. 2026InterPReT: Interactive Policy Restructuring and Training Enable Effective Imitation Learning from Laypersons
  8. 2023A Closer Look at Reward Decomposition for High-Level Robotic Explanations