Explainable RL Policies by Distilling to Locally-Specialized Linear Policies with Voronoi State Partitioning

• URL: http://arxiv.org/abs/2511.13322v1
• Date: Mon, 17 Nov 2025 12:58:38 GMT
• Title: Explainable RL Policies by Distilling to Locally-Specialized Linear Policies with Voronoi State Partitioning
• Abstract summary: We propose a new model-agnostic method to divide the state space into regions where a simplified, human-understandable model can operate in.<n>In this paper, we use Voronoi partitioning to find regions where linear models can achieve similar performance to the original con- troller.
• Score: 5.417332705560665
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Reinforcement Learning is one of the state-of-the-art methods for producing near-optimal system controllers. However, deep RL algorithms train a deep neural network, that lacks transparency, which poses challenges when the controller has to meet regulations, or foster trust. To alleviate this, one could transfer the learned behaviour into a model that is human-readable by design using knowledge distilla- tion. Often this is done with a single model which mimics the original model on average but could struggle in more dynamic situations. A key challenge is that this simpler model should have the right balance be- tween flexibility and complexity or right balance between balance bias and accuracy. We propose a new model-agnostic method to divide the state space into regions where a simplified, human-understandable model can operate in. In this paper, we use Voronoi partitioning to find regions where linear models can achieve similar performance to the original con- troller. We evaluate our approach on a gridworld environment and a classic control task. We observe that our proposed distillation to locally- specialized linear models produces policies that are explainable and show that the distillation matches or even slightly outperforms the black-box policy they are distilled from.

Related papers

• Position: Weight Space Should Be a First-Class Generative AI Modality [67.10702320971893]
  This paper argues that model checkpoints should be treated as a first-class data modality.<n>It argues that generative modeling in weight space should be standardized as a core machine learning primitive.<n>Our goal is to shift the community's default mindset from optimizing models per task to sampling models from learned weight distributions.
  arXiv  Detail & Related papers  (2026-05-18T16:38:26Z)
• Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models [5.417332705560665]
  We introduce a new model-agnostic method called Critic-Driven Voronoi State Partitioning.<n>By exploiting the critic value network of the original policy, we introduce new subpolicies in regions with insufficient value.<n>We validate our approach on several well known benchmarks and proof that this distillation approaches the original policy using a reasonable sized set of linear functions.
  arXiv  Detail & Related papers  (2026-05-14T14:38:56Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning [2.9158689853305693]
  We consider a model-based reinforcement learning algorithm that infers the system dynamics from the available data and performs policy optimization on imaginary model rollouts. This approach is vulnerable to exploiting model errors which can lead to catastrophic failures on the real system. We show that better performance can be obtained with a single well-calibrated autoregressive model on the D4RL benchmark.
  arXiv  Detail & Related papers  (2024-02-05T10:18:15Z)
• Predictable MDP Abstraction for Unsupervised Model-Based RL [93.91375268580806]
  We propose predictable MDP abstraction (PMA) Instead of training a predictive model on the original MDP, we train a model on a transformed MDP with a learned action space. We theoretically analyze PMA and empirically demonstrate that PMA leads to significant improvements over prior unsupervised model-based RL approaches.
  arXiv  Detail & Related papers  (2023-02-08T07:37:51Z)
• Bridging the Model-Reality Gap with Lipschitz Network Adaptation [22.499090318313662]
  As robots venture into the real world, they are subject to unmodeled dynamics and disturbances. Traditional model-based control approaches have been proven successful in relatively static and known operating environments. We propose a method that bridges the model-reality gap and enables the application of model-based approaches even if dynamic uncertainties are present.
  arXiv  Detail & Related papers  (2021-12-07T15:12:49Z)
• Self-Supervised Hybrid Inference in State-Space Models [0.0]
  We perform approximate inference in state-space models that allow for nonlinear higher-order Markov chains in latent space. We do not rely on an additional parameterization of the generative model or supervision via uncorrupted observations or ground truth latent states. We obtain competitive results on the chaotic Lorenz system compared to a fully supervised approach and outperform a method based on variational inference.
  arXiv  Detail & Related papers  (2021-07-28T13:26:14Z)
• COMBO: Conservative Offline Model-Based Policy Optimization [120.55713363569845]
  Uncertainty estimation with complex models, such as deep neural networks, can be difficult and unreliable. We develop a new model-based offline RL algorithm, COMBO, that regularizes the value function on out-of-support state-actions. We find that COMBO consistently performs as well or better as compared to prior offline model-free and model-based methods.
  arXiv  Detail & Related papers  (2021-02-16T18:50:32Z)
• VAE-LIME: Deep Generative Model Based Approach for Local Data-Driven Model Interpretability Applied to the Ironmaking Industry [70.10343492784465]
  It is necessary to expose to the process engineer, not solely the model predictions, but also their interpretability. Model-agnostic local interpretability solutions based on LIME have recently emerged to improve the original method. We present in this paper a novel approach, VAE-LIME, for local interpretability of data-driven models forecasting the temperature of the hot metal produced by a blast furnace.
  arXiv  Detail & Related papers  (2020-07-15T07:07:07Z)
• Model-Free Voltage Regulation of Unbalanced Distribution Network Based on Surrogate Model and Deep Reinforcement Learning [9.984416150031217]
  This paper develops a model-free approach based on the surrogate model and deep reinforcement learning (DRL) We have also extended it to deal with unbalanced three-phase scenarios.
  arXiv  Detail & Related papers  (2020-06-24T18:49:41Z)
• MOPO: Model-based Offline Policy Optimization [183.6449600580806]
  offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. We show that an existing model-based RL algorithm already produces significant gains in the offline setting. We propose to modify the existing model-based RL methods by applying them with rewards artificially penalized by the uncertainty of the dynamics.
  arXiv  Detail & Related papers  (2020-05-27T08:46:41Z)
• Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning [75.56839075060819]
  Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sample-inefficient and brittle. In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline.
  arXiv  Detail & Related papers  (2020-05-21T19:47:05Z)
• Bootstrapped model learning and error correction for planning with uncertainty in model-based RL [1.370633147306388]
  A natural aim is to learn a model that reflects accurately the dynamics of the environment. This paper explores the problem of model misspecification through uncertainty-aware reinforcement learning agents. We propose a bootstrapped multi-headed neural network that learns the distribution of future states and rewards.
  arXiv  Detail & Related papers  (2020-04-15T15:41:21Z)

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.