mlsanityData to 14 Oct 2026

Personalized Path Recourse for Reinforcement Learning Agents

arXiv 2312.08724 ↗First posted 14 Dec 2023cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces Personalized Path Recourse, a novel method that generates recourse paths for a reinforcement learning agent. The goal is to edit a given path of actions to achieve desired goals (e.g., better outcomes compared to the agent's original path) while ensuring a high similarity to the agent's original paths and being personalized to the agent. Personalization refers to the extent to which the new path is tailored to the agent's observed behavior patterns from their policy function. We train a personalized recourse agent to generate such personalized paths, which are obtained using reward functions that consider the goal, similarity, and personalization. The proposed method is applicable to both reinforcement learning and supervised learning settings for correcting or improving sequences of actions or sequences of data to achieve a pre-determined goal. The method is evaluated in various settings. Experiments show that our model not only recourses for a better outcome but also adapts to different agents' behavior.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 49 references that are in the map. First posted on arXiv 14 Dec 2023.

Builds on

41 of 49 references.

References · 41

  1. 2017Hindsight Experience Replaycited by 1,136
  2. 2015Prioritized Experience Replaycited by 1,099
  3. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  4. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  5. 2017Deep Reinforcement Learning that Matterscited by 754
  6. 2018Actionable Recourse in Linear Classificationcited by 328
  7. 2019Counterfactual Visual Explanationscited by 313
  8. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  9. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
  10. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  11. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 211
  12. 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
29 more
  1. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  2. 2020Multi-Objective Counterfactual Explanationscited by 157
  3. 2017Imagination-Augmented Agents for Deep Reinforcement Learningcited by 140
  4. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 131
  5. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  6. 2021Counterfactual Generative Networkscited by 111
  7. 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 106
  8. 2021Towards Robust and Reliable Algorithmic Recoursecited by 102
  9. 2018Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Searchcited by 82
  10. 2020Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Textcited by 75
  11. 2020Instance-based Counterfactual Explanations for Time Series Classificationcited by 64
  12. 2020Counterfactual Explanations for Machine Learning on Multivariate Time Series Datacited by 49
  13. 2020Decisions, Counterfactual Explanations and Strategic Behaviorcited by 44
  14. 2018Interpretable Credit Application Predictions With Counterfactual Explanationscited by 43
  15. 2021Counterfactual Explanations in Sequential Decision Making Under Uncertaintycited by 37
  16. 2020CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Netscited by 29
  17. 2021Conditional Generative Models for Counterfactual Explanationscited by 28
  18. 2021Amortized Generation of Sequential Algorithmic Recourses for Black-box Modelscited by 24
  19. 2021Discovering Diverse Nearly Optimal Policies with Successor Featurescited by 20
  20. 2020Learning Models for Actionable Recoursecited by 18
  21. 2021Designing Counterfactual Generators using Deep Model Inversioncited by 15
  22. 2019Counterfactual States for Atari Agents via Generative Deep Learningcited by 14
  23. 2021Bayesian Persuasion for Algorithmic Recoursecited by 14
  24. 2021DiCE4EL: Interpreting Process Predictions using a Milestone-Aware Counterfactual Approachcited by 13
  25. 2022Diverse Counterfactual Explanations for Anomaly Detection in Time Seriescited by 10
  26. 2022Personalized Algorithmic Recourse with Preference Elicitationcited by 9
  27. 2022Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesiscited by 8
  28. 2022Explaining Reinforcement Learning Policies through Counterfactual Trajectoriescited by 7
  29. 2023RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learningcited by 6

Built on by

Not cited yet.