mlsanityData to 14 Oct 2026

Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning

arXiv 2309.06097 ↗First posted 12 Sep 2023cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making problems. However, existing DRL agents make decisions in an opaque fashion, hindering the user from establishing trust and scrutinizing weaknesses of the agents. While recent research has developed Interpretable Policy Extraction (IPE) methods for explaining how an agent takes actions, their explanations are often inconsistent with the agent's behavior and thus, frequently fail to explain. To tackle this issue, we propose a novel method, Fidelity-Induced Policy Extraction (FIPE). Specifically, we start by analyzing the optimization mechanism of existing IPE methods, elaborating on the issue of ignoring consistency while increasing cumulative rewards. We then design a fidelity-induced mechanism by integrate a fidelity measurement into the reinforcement learning feedback. We conduct experiments in the complex control environment of StarCraft II, an arena typically avoided by current IPE methods. The experiment results demonstrate that FIPE outperforms the baselines in terms of interaction performance and consistency, meanwhile easy to understand.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 38 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

21 of 38 references.

References · 21

  1. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  2. 2018Rethinking the Value of Network Pruningcited by 599
  3. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  4. 2018Residual Reinforcement Learning for Robot Controlcited by 274
  5. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 268
  6. 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 260
  7. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
  8. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 190
  9. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  10. 2020Explainable Reinforcement Learning: A Surveycited by 141
  11. 2016Measuring Neural Net Robustness with Constraintscited by 90
  12. 2018Toward Interpretable Deep Reinforcement Learning with Linear Model U-Treescited by 65
9 more
  1. 2019Explainability in Human-Agent Systemscited by 34
  2. 2019Mo"ET: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learningcited by 12
  3. 2022MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learningcited by 12
  4. 2020Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learningcited by 10
  5. 2021Deep Reinforcement Learning for Black-Box Testing of Android Appscited by 10
  6. 2022Explainable Action Advising for Multi-Agent Reinforcement Learningcited by 10
  7. 2020Designing Interpretable Approximations to Deep Reinforcement Learningcited by 6
  8. 2019Complementary reinforcement learning towards explainable agentscited by 5
  9. 2021Neural-to-Tree Policy Distillation with Policy Improvement Criterioncited by 5

Built on by

Not cited yet.