Selecting Decision-Relevant Concepts in Reinforcement Learning

• URL: http://arxiv.org/abs/2604.04808v1
• Date: Mon, 06 Apr 2026 16:12:42 GMT
• Title: Selecting Decision-Relevant Concepts in Reinforcement Learning
• Abstract summary: Training interpretable concept-based policies require practitioners to manually select which human-understandable concepts an agent should reason with when making sequential decisions.<n>This selection demands domain expertise, is time-consuming and costly, scales poorly with the number of candidates, and provides no performance guarantees.<n>We propose the first algorithms for principled automatic concept selection in sequential decision-making.
• Score: 11.811571265392294
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training interpretable concept-based policies requires practitioners to manually select which human-understandable concepts an agent should reason with when making sequential decisions. This selection demands domain expertise, is time-consuming and costly, scales poorly with the number of candidates, and provides no performance guarantees. To overcome this limitation, we propose the first algorithms for principled automatic concept selection in sequential decision-making. Our key insight is that concept selection can be viewed through the lens of state abstraction: intuitively, a concept is decision-relevant if removing it would cause the agent to confuse states that require different actions. As a result, agents should rely on decision-relevant concepts; states with the same concept representation should share the same optimal action, which preserves the optimal decision structure of the original state space. This perspective leads to the Decision-Relevant Selection (DRS) algorithm, which selects a subset of concepts from a candidate set, along with performance bounds relating the selected concepts to the performance of the resulting policy. Empirically, DRS automatically recovers manually curated concept sets while matching or exceeding their performance, and improves the effectiveness of test-time concept interventions across reinforcement learning benchmarks and real-world healthcare environments.

Related papers

• ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation [19.876384055954865]
  ConceptTree is a framework that reframes high-level manipulation skill selection as reasoning over human-interpretable concepts.<n>We evaluate our approach on a set of real-world robotic manipulation tasks with increasing complexity.
  arXiv  Detail & Related papers  (2026-07-20T12:02:30Z)
• Unweighted ranking for value-based decision making with uncertainty [5.607590231264275]
  We introduce the Fuzzy-Unweighted Value-Based Decision Making (FUW-VBDM) framework.<n>Agents incorporate both quantitative and qualitative criteria to generate human-centred decisions.<n>We present Rankzzy, a customizable unweighted ranking method that integrates fuzzy-based reasoning to quantify uncertainty.
  arXiv  Detail & Related papers  (2026-05-13T14:36:17Z)
• Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition [81.2779530670268]
  Vision-Language Models (VLMs) have significantly advanced zero-shot image recognition.<n>This paper enhances prompt by incorporating class-specific concepts.<n>Our method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-03-09T03:11:11Z)
• Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models [15.97013792698305]
  Concept Bottleneck Models (CBMs) decompose image classification into a process governed by interpretable, human-readable concepts.<n>We introduce a dynamic, agent-based approach that adjusts the concept bank in response to environmental feedback.<n>We also propose Conditional Concept Bottleneck Models (CoCoBMs) to overcome the limitations in traditional CBMs' concept scoring mechanisms.
  arXiv  Detail & Related papers  (2025-06-02T05:25:52Z)
• Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models [57.86303579812877]
  Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Existing approaches often require numerous human interventions per image to achieve strong performances. We introduce a trainable concept realignment intervention module, which leverages concept relations to realign concept assignments post-intervention.
  arXiv  Detail & Related papers  (2024-05-02T17:59:01Z)
• Online Decision Mediation [72.80902932543474]
  Consider learning a decision support assistant to serve as an intermediary between (oracle) expert behavior and (imperfect) human behavior. In clinical diagnosis, fully-autonomous machine behavior is often beyond ethical affordances.
  arXiv  Detail & Related papers  (2023-10-28T05:59:43Z)
• Explainability's Gain is Optimality's Loss? -- How Explanations Bias Decision-making [0.0]
  Explanations help to facilitate communication between the algorithm and the human decision-maker. Feature-based explanations' semantics of causal models induce leakage from the decision-maker's prior beliefs. Such differences can lead to sub-optimal and biased decision outcomes.
  arXiv  Detail & Related papers  (2022-06-17T11:43:42Z)
• A Justice-Based Framework for the Analysis of Algorithmic Fairness-Utility Trade-Offs [0.0]
  In prediction-based decision-making systems, different perspectives can be at odds. The short-term business goals of the decision makers are often in conflict with the decision subjects' wish to be treated fairly. We propose a framework to make these value-laden choices clearly visible.
  arXiv  Detail & Related papers  (2022-06-06T20:31:55Z)
• Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies [79.60322329952453]
  We show how to develop interpretable representations of how agents make decisions. By understanding the decision-making processes underlying a set of observed trajectories, we cast the policy inference problem as the inverse to this online learning problem. We introduce a practical algorithm for retrospectively estimating such perceived effects, alongside the process through which agents update them. Through application to the analysis of UNOS organ donation acceptance decisions, we demonstrate that our approach can bring valuable insights into the factors that govern decision processes and how they change over time.
  arXiv  Detail & Related papers  (2022-03-14T17:40:42Z)
• Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment [79.5678820246642]
  We show that certain action-value methods are more sample efficient than policy-gradient methods on transfer problems that require only sparse changes to a sequence of previously optimal decisions. We generalize the recently proposed societal decision-making framework as a more granular formalism than the Markov decision process.
  arXiv  Detail & Related papers  (2021-06-28T21:29:13Z)
• Conceptualising Contestability: Perspectives on Contesting Algorithmic Decisions [18.155121103400333]
  We describe and analyse the perspectives of people and organisations who made submissions in response to Australia's proposed AI Ethics Framework' Our findings reveal that while the nature of contestability is disputed, it is seen as a way to protect individuals, and it resembles contestability in relation to human decision-making.
  arXiv  Detail & Related papers  (2021-02-23T05:13:18Z)
• Inverse Active Sensing: Modeling and Understanding Timely Decision-Making [111.07204912245841]
  We develop a framework for the general setting of evidence-based decision-making under endogenous, context-dependent time pressure. We demonstrate how it enables modeling intuitive notions of surprise, suspense, and optimality in decision strategies.
  arXiv  Detail & Related papers  (2020-06-25T02:30:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.