Interpretable by Design: Query-Specific Neural Modules for Explainable Reinforcement Learning

• URL: http://arxiv.org/abs/2511.08749v1
• Date: Thu, 13 Nov 2025 01:05:29 GMT
• Title: Interpretable by Design: Query-Specific Neural Modules for Explainable Reinforcement Learning
• Authors: Mehrdad Zakershahrak,
• Abstract summary: We architect RL systems as inference engines that can answer diverse queries about their environment.<n>We introduce Query Conditioned Deterministic Inference Networks (QDIN), a unified architecture that treats different types of queries as first-class citizens.<n>Our key empirical finding reveals a fundamental decoupling: inference accuracy can reach near-perfect levels even when control performance remains suboptimal.
• Score: 0.3655021726150367
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning has traditionally focused on a singular objective: learning policies that select actions to maximize reward. We challenge this paradigm by asking: what if we explicitly architected RL systems as inference engines that can answer diverse queries about their environment? In deterministic settings, trained agents implicitly encode rich knowledge about reachability, distances, values, and dynamics - yet current architectures are not designed to expose this information efficiently. We introduce Query Conditioned Deterministic Inference Networks (QDIN), a unified architecture that treats different types of queries (policy, reachability, paths, comparisons) as first-class citizens, with specialized neural modules optimized for each inference pattern. Our key empirical finding reveals a fundamental decoupling: inference accuracy can reach near-perfect levels (99% reachability IoU) even when control performance remains suboptimal (31% return), suggesting that the representations needed for accurate world knowledge differ from those required for optimal control. Experiments demonstrate that query specialized architectures outperform both unified models and post-hoc extraction methods, while maintaining competitive control performance. This work establishes a research agenda for RL systems designed from inception as queryable knowledge bases, with implications for interpretability, verification, and human-AI collaboration.

Related papers

• Breaking Robustness Barriers in Cognitive Diagnosis: A One-Shot Neural Architecture Search Perspective [19.30893604363489]
  We propose One-Shot neural architecture search method for Cognitive Diagnosis.<n> OSCD operates through two distinct stages: training and searching.<n>In searching stage, we formulate the optimal architecture search under heterogeneous noise scenarios.
  arXiv  Detail & Related papers  (2026-01-08T13:17:40Z)
• An Integrated Approach to Neural Architecture Search for Deep Q-Networks [1.516610503825416]
  NAS-DQN is an agent that integrates a learned neural architecture search controller directly into the DRL training loop.<n>We evaluate NAS-DQN against three fixed-architecture baselines and a random search control on a continuous control task.<n>Our results demonstrate that NAS-DQN achieves superior final performance, sample efficiency, and policy stability while incurring negligible computational overhead.
  arXiv  Detail & Related papers  (2025-10-22T07:17:31Z)
• Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation [18.99847259801634]
  We propose Reinforcement Learning from Augmented Generation (RLAG) to embed domain knowledge into large language models.<n>Our approach iteratively cycles between sampling generations and optimize the model through calculated rewards.<n> Experimental results across medical, legal, astronomy, and current events datasets demonstrate that our proposed method significantly outperforms baseline approaches.
  arXiv  Detail & Related papers  (2025-09-24T14:30:16Z)
• SoftPipe: A Soft-Guided Reinforcement Learning Framework for Automated Data Preparation [10.764970149373845]
  We introduce SoftPipe, a novel RL framework that replaces rigid hard constraints'' with a flexible soft guidance'' paradigm.<n>We demonstrate that SoftPipe achieves up to a 13.9% improvement in pipeline quality and 2.8$times$ faster convergence compared to existing methods.
  arXiv  Detail & Related papers  (2025-07-18T07:43:22Z)
• Scalable In-Context Q-Learning [68.9917436397079]
  We propose textbfScalable textbfIn-textbfContext textbfQ-textbfLearning (textbfSICQL) to steer in-context reinforcement learning.<n>textbfSICQL harnesses dynamic programming and world modeling to steer ICRL toward efficient reward and task generalization.
  arXiv  Detail & Related papers  (2025-06-02T04:21:56Z)
• Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment [10.814585613336778]
  Causal representation learning aims to combine the core strengths of machine learning and causality. This thesis investigates what is possible for CRL without direct supervision, and thus contributes to its theoretical foundations.
  arXiv  Detail & Related papers  (2024-06-19T09:14:40Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• Deep networks for system identification: a Survey [56.34005280792013]
  System identification learns mathematical descriptions of dynamic systems from input-output data. Main aim of the identified model is to predict new data from previous observations. We discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks.
  arXiv  Detail & Related papers  (2023-01-30T12:38:31Z)
• INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL [90.06845886194235]
  We propose a modified objective for model-based reinforcement learning (RL) We integrate a term inspired by variational empowerment into a state-space model based on mutual information. We evaluate the approach on a suite of vision-based robot control tasks with natural video backgrounds.
  arXiv  Detail & Related papers  (2022-04-18T23:09:23Z)
• elBERto: Self-supervised Commonsense Learning for Question Answering [131.51059870970616]
  We propose a Self-supervised Bidirectional Representation Learning of Commonsense framework, which is compatible with off-the-shelf QA model architectures. The framework comprises five self-supervised tasks to force the model to fully exploit the additional training signals from contexts containing rich commonsense. elBERto achieves substantial improvements on out-of-paragraph and no-effect questions where simple lexical similarity comparison does not help.
  arXiv  Detail & Related papers  (2022-03-17T16:23:45Z)
• LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction [42.38793195337463]
  We propose a novel learning-based ensemble approach named LENAS, which integrates neural architecture search with knowledge distillation for 3D radiotherapy dose prediction. Our approach starts by exhaustively searching each block from an enormous architecture space to identify multiple architectures that exhibit promising performance. To mitigate the complexity introduced by the model ensemble, we adopt the teacher-student paradigm, leveraging the diverse outputs from multiple learned networks as supervisory signals.
  arXiv  Detail & Related papers  (2021-06-12T10:08:52Z)
• Information Directed Reward Learning for Reinforcement Learning [64.33774245655401]
  We learn a model of the reward function that allows standard RL algorithms to achieve high expected return with as few expert queries as possible. In contrast to prior active reward learning methods designed for specific types of queries, IDRL naturally accommodates different query types. We support our findings with extensive evaluations in multiple environments and with different types of queries.
  arXiv  Detail & Related papers  (2021-02-24T18:46:42Z)

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.